{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/prompt-engineering","name":"Prompt Engineering","slug":"prompt-engineering","description_markdown":"**Prompt engineering** is the process of designing and refining the prompts used to generate text from language models, such as GPT-3 or similar models. The goal of prompt engineering is to improve the quality and relevance of the generated text by carefully crafting the prompts to elicit the desired responses from the model.\r\n\r\nPrompt engineering involves several steps, including selecting the appropriate model architecture and parameters, designing the prompt format and structure, selecting the appropriate task and training data, and fine-tuning the model using the selected prompt and data.\r\n\r\nPrompt engineering is a crucial step in the development of language models, as it can greatly influence the quality and effectiveness of the model's responses. By carefully designing and refining the prompts used to generate text, researchers and developers can improve the accuracy and relevance of the model's output, making it more useful for a wide range of applications, including chatbots, language translation, content creation, and more.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1236,"papers_with_code":454,"benchmarks":16,"benchmark_tables_in_archive":16,"benchmark_tables_shown":16,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":16,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/prompt-engineering-on-imagenet","slug":"prompt-engineering-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":15,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-caltech-101","slug":"prompt-engineering-on-caltech-101","dataset":"Caltech-101","dataset_url":"/dataset/caltech-101","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-dtd","slug":"prompt-engineering-on-dtd","dataset":"DTD","dataset_url":"/dataset/dtd","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-eurosat","slug":"prompt-engineering-on-eurosat","dataset":"EuroSAT","dataset_url":"/dataset/eurosat","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"MMRL++","paper_title":"MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models","paper_url":"/paper/mmrl-parameter-efficient-and-interaction","paper_date":"2025-05-15","arxiv_id":"2505.10088","code_links":[{"title":"yunncheng/MMRL","url":"https://github.com/yunncheng/MMRL"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-fgvc-aircraft","slug":"prompt-engineering-on-fgvc-aircraft","dataset":"FGVC-Aircraft","dataset_url":"/dataset/fgvc-aircraft-1","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-oxford-102-flower","slug":"prompt-engineering-on-oxford-102-flower","dataset":"Oxford 102 Flower","dataset_url":"/dataset/oxford-102-flower","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-oxford-iiit-pet-dataset","slug":"prompt-engineering-on-oxford-iiit-pet-dataset","dataset":"Oxford-IIIT Pet Dataset","dataset_url":"/dataset/oxford-iiit-pets","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-stanford-cars-1","slug":"prompt-engineering-on-stanford-cars-1","dataset":"Stanford Cars","dataset_url":"/dataset/stanford-cars","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-sun397","slug":"prompt-engineering-on-sun397","dataset":"SUN397","dataset_url":"/dataset/sun397","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-ucf101","slug":"prompt-engineering-on-ucf101","dataset":"UCF101","dataset_url":"/dataset/ucf101","rows_in_archive":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-food-101","slug":"prompt-engineering-on-food-101","dataset":"Food-101","dataset_url":"/dataset/food-101","rows_in_archive":13,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper_title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","paper_url":"/paper/promptkd-unsupervised-prompt-distillation-for","paper_date":"2024-03-05","arxiv_id":"2403.02781","code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-imagenet-a","slug":"prompt-engineering-on-imagenet-a","dataset":"ImageNet-A","dataset_url":"/dataset/imagenet-a","rows_in_archive":9,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"POMP","paper_title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","paper_url":"/paper/prompt-pre-training-with-twenty-thousand-1","paper_date":"2023-04-10","arxiv_id":"2304.04704","code_links":[{"title":"amazon-science/prompt-pretraining","url":"https://github.com/amazon-science/prompt-pretraining"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prompt-pre-training-with-twenty-thousand-1#ran","syntology_url":"https://syntology.ai/paper/2304.04704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04704"}},"official":{"repos":["amazon-science/prompt-pretraining"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/prompt-engineering-on-imagenet-r","slug":"prompt-engineering-on-imagenet-r","dataset":"ImageNet-R","dataset_url":"/dataset/imagenet-r","rows_in_archive":9,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"POMP","paper_title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","paper_url":"/paper/prompt-pre-training-with-twenty-thousand-1","paper_date":"2023-04-10","arxiv_id":"2304.04704","code_links":[{"title":"amazon-science/prompt-pretraining","url":"https://github.com/amazon-science/prompt-pretraining"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prompt-pre-training-with-twenty-thousand-1#ran","syntology_url":"https://syntology.ai/paper/2304.04704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04704"}},"official":{"repos":["amazon-science/prompt-pretraining"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/prompt-engineering-on-imagenet-s","slug":"prompt-engineering-on-imagenet-s","dataset":"ImageNet-S","dataset_url":"/dataset/imagenet-s","rows_in_archive":9,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"POMP","paper_title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","paper_url":"/paper/prompt-pre-training-with-twenty-thousand-1","paper_date":"2023-04-10","arxiv_id":"2304.04704","code_links":[{"title":"amazon-science/prompt-pretraining","url":"https://github.com/amazon-science/prompt-pretraining"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prompt-pre-training-with-twenty-thousand-1#ran","syntology_url":"https://syntology.ai/paper/2304.04704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04704"}},"official":{"repos":["amazon-science/prompt-pretraining"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/prompt-engineering-on-imagenet-v2","slug":"prompt-engineering-on-imagenet-v2","dataset":"ImageNet V2","dataset_url":"/dataset/imagenet","rows_in_archive":8,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"HPT++","paper_title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","paper_url":"/paper/hpt-hierarchically-prompting-vision-language","paper_date":"2024-08-27","arxiv_id":"2408.14812","code_links":[{"title":"vill-lab/2024-aaai-hpt","url":"https://github.com/vill-lab/2024-aaai-hpt"},{"title":"ThomasWangY/2024-AAAI-HPT","url":"https://github.com/ThomasWangY/2024-AAAI-HPT"}],"syntology":null}},{"leaderboard":"/sota/prompt-engineering-on-imagenet-21k","slug":"prompt-engineering-on-imagenet-21k","dataset":"ImageNet-21k","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"POMP","paper_title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","paper_url":"/paper/prompt-pre-training-with-twenty-thousand-1","paper_date":"2023-04-10","arxiv_id":"2304.04704","code_links":[{"title":"amazon-science/prompt-pretraining","url":"https://github.com/amazon-science/prompt-pretraining"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prompt-pre-training-with-twenty-thousand-1#ran","syntology_url":"https://syntology.ai/paper/2304.04704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04704"}},"official":{"repos":["amazon-science/prompt-pretraining"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/oxford-102-flower","name":"Oxford 102 Flower","full_name":"102 Category Flower Dataset","num_papers_in_archive":1307},{"url":"/dataset/dtd","name":"DTD","full_name":"Describable Textures Dataset","num_papers_in_archive":870},{"url":"/dataset/food-101","name":"Food-101","full_name":"","num_papers_in_archive":805},{"url":"/dataset/stanford-cars","name":"Stanford Cars","full_name":"","num_papers_in_archive":790},{"url":"/dataset/caltech-101","name":"Caltech-101","full_name":"","num_papers_in_archive":709},{"url":"/dataset/eurosat","name":"EuroSAT","full_name":"EuroSAT","num_papers_in_archive":687},{"url":"/dataset/fgvc-aircraft-1","name":"FGVC-Aircraft","full_name":"","num_papers_in_archive":520},{"url":"/dataset/imagenet-r","name":"ImageNet-R","full_name":"ImageNet-Rendition","num_papers_in_archive":481},{"url":"/dataset/imagenet-a","name":"ImageNet-A","full_name":"","num_papers_in_archive":431},{"url":"/dataset/oxford-iiit-pets","name":"Oxford-IIIT Pet Dataset","full_name":"Oxford-IIIT Pet Dataset","num_papers_in_archive":90},{"url":"/dataset/oxford-iiit-pets-1","name":"Oxford-IIIT Pets","full_name":"","num_papers_in_archive":59},{"url":"/dataset/sun397","name":"SUN397","full_name":"SUN397","num_papers_in_archive":52},{"url":"/dataset/imagenet-s","name":"ImageNet-S","full_name":"ImageNet Semantic Segmentation","num_papers_in_archive":43},{"url":"/dataset/omnibenchmark","name":"OmniBenchmark","full_name":"","num_papers_in_archive":29}],"subtasks":[{"url":"/task/visual-prompting","name":"Visual Prompting"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":13,"rows_per_page":100,"shown":100,"of":1236,"of_with_code":454,"tagged_in_all":1236,"counts":{"archive_papers_tagged":1236,"with_a_code_link":454,"where_syntology_ran_a_sample":143,"not_listed_spam_title":0,"listed":1236,"listed_where_code_ran":143,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":108,"every_run_a_failure_of_syntologys_instrument":35,"listed_with_a_run_with_no_instrument_failure":108,"listed_every_run_a_failure_of_syntologys_instrument":35,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","repositories_listed":82,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":2,"n_instrument":14,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":16,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}},"official":{"repos":["openai/CLIP"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/learning-to-prompt-for-vision-language-models","slug":"learning-to-prompt-for-vision-language-models","title":"Learning to Prompt for Vision-Language Models","date":"2021-09-02","arxiv_id":"2109.01134","repositories_listed":18,"syntology":{"n":12,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/learning-to-prompt-for-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2109.01134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01134"}},"official":{"repos":["kaiyangzhou/coop"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/conditional-prompt-learning-for-vision","slug":"conditional-prompt-learning-for-vision","title":"Conditional Prompt Learning for Vision-Language Models","date":"2022-03-10","arxiv_id":"2203.05557","repositories_listed":12,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/conditional-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2203.05557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05557"}},"official":{"repos":["kaiyangzhou/coop"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/gpt-understands-too","slug":"gpt-understands-too","title":"GPT Understands, Too","date":"2021-03-18","arxiv_id":"2103.10385","repositories_listed":10,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-understands-too#ran","syntology_url":"https://syntology.ai/paper/2103.10385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10385"}},"official":{"repos":["THUDM/P-tuning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multitask-prompted-training-enables-zero-shot-1","slug":"multitask-prompted-training-enables-zero-shot-1","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","date":"2021-10-15","arxiv_id":"2110.08207","repositories_listed":8,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multitask-prompted-training-enables-zero-shot-1#ran","syntology_url":"https://syntology.ai/paper/2110.08207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08207"}},"official":{"repos":["bigscience-workshop/promptsource","bigscience-workshop/t-zero"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visual-prompt-tuning","slug":"visual-prompt-tuning","title":"Visual Prompt Tuning","date":"2022-03-23","arxiv_id":"2203.12119","repositories_listed":6,"syntology":{"n":27,"n_ran":18,"n_constructed":12,"n_ran_checked":16,"n_instrument":2,"n_unverified":9,"n_honours":1,"n_violates":1,"n_no_contract":14,"n_pointer_only":15,"phrase":"18 ran (of which 12 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/visual-prompt-tuning#ran","syntology_url":"https://syntology.ai/paper/2203.12119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12119"}},"official":{"repos":["KMnP/vpt"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/gpt-takes-the-bar-exam","slug":"gpt-takes-the-bar-exam","title":"GPT Takes the Bar Exam","date":"2022-12-29","arxiv_id":"2212.14402","repositories_listed":5,"syntology":null},{"url":"/paper/large-language-models-are-human-level-prompt","slug":"large-language-models-are-human-level-prompt","title":"Large Language Models Are Human-Level Prompt Engineers","date":"2022-11-03","arxiv_id":"2211.01910","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-are-human-level-prompt#ran","syntology_url":"https://syntology.ai/paper/2211.01910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01910"}},"official":{"repos":["keirp/automatic_prompt_engineer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/langgpt-rethinking-structured-reusable-prompt","slug":"langgpt-rethinking-structured-reusable-prompt","title":"LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language","date":"2024-02-26","arxiv_id":"2402.16929","repositories_listed":4,"syntology":null},{"url":"/paper/ip-adapter-text-compatible-image-prompt","slug":"ip-adapter-text-compatible-image-prompt","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","date":"2023-08-13","arxiv_id":"2308.06721","repositories_listed":4,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ip-adapter-text-compatible-image-prompt#ran","syntology_url":"https://syntology.ai/paper/2308.06721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06721"}},"official":null}},{"url":"/paper/mme-a-comprehensive-evaluation-benchmark-for","slug":"mme-a-comprehensive-evaluation-benchmark-for","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","date":"2023-06-23","arxiv_id":"2306.13394","repositories_listed":4,"syntology":null},{"url":"/paper/differentiable-prompt-makes-pre-trained","slug":"differentiable-prompt-makes-pre-trained","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","date":"2021-08-30","arxiv_id":"2108.13161","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/differentiable-prompt-makes-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2108.13161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.13161"}},"official":{"repos":["zjunlp/DART"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/the-prompt-report-a-systematic-survey-of","slug":"the-prompt-report-a-systematic-survey-of","title":"The Prompt Report: A Systematic Survey of Prompting Techniques","date":"2024-06-06","arxiv_id":"2406.06608","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-prompt-report-a-systematic-survey-of#ran","syntology_url":"https://syntology.ai/paper/2406.06608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06608"}},"official":{"repos":["trigaten/Prompt_Systematic_Review","trigaten/the_prompt_report","trigaten/learn_prompting"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/chain-of-thought-reasoning-without-prompting","slug":"chain-of-thought-reasoning-without-prompting","title":"Chain-of-Thought Reasoning Without Prompting","date":"2024-02-15","arxiv_id":"2402.10200","repositories_listed":3,"syntology":null},{"url":"/paper/optimizing-prompts-for-text-to-image-1","slug":"optimizing-prompts-for-text-to-image-1","title":"Optimizing Prompts for Text-to-Image Generation","date":"2022-12-19","arxiv_id":"2212.09611","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/optimizing-prompts-for-text-to-image-1#ran","syntology_url":"https://syntology.ai/paper/2212.09611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09611"}},"official":{"repos":["microsoft/lmops"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/maple-multi-modal-prompt-learning","slug":"maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","arxiv_id":"2210.03117","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/maple-multi-modal-prompt-learning#ran","syntology_url":"https://syntology.ai/paper/2210.03117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03117"}},"official":{"repos":["muzairkhattak/multimodal-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ask-me-anything-a-simple-strategy-for","slug":"ask-me-anything-a-simple-strategy-for","title":"Ask Me Anything: A simple strategy for prompting language models","date":"2022-10-05","arxiv_id":"2210.02441","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ask-me-anything-a-simple-strategy-for#ran","syntology_url":"https://syntology.ai/paper/2210.02441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02441"}},"official":{"repos":["hazyresearch/ama_prompting"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/clip-adapter-better-vision-language-models","slug":"clip-adapter-better-vision-language-models","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","date":"2021-10-09","arxiv_id":"2110.04544","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-adapter-better-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2110.04544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04544"}},"official":{"repos":["gaopengcuhk/clip-adapter"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/time-series-forecasting-as-reasoning-a-slow","slug":"time-series-forecasting-as-reasoning-a-slow","title":"Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs","date":"2025-06-12","arxiv_id":"2506.10630","repositories_listed":2,"syntology":null},{"url":"/paper/risk-aware-driving-scenario-analysis-with","slug":"risk-aware-driving-scenario-analysis-with","title":"From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios","date":"2025-02-04","arxiv_id":"2502.02145","repositories_listed":2,"syntology":null},{"url":"/paper/a-comparison-of-prompt-engineering-techniques","slug":"a-comparison-of-prompt-engineering-techniques","title":"A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service Robotics","date":"2024-10-30","arxiv_id":"2410.22997","repositories_listed":2,"syntology":null},{"url":"/paper/hpt-hierarchically-prompting-vision-language","slug":"hpt-hierarchically-prompting-vision-language","title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","date":"2024-08-27","arxiv_id":"2408.14812","repositories_listed":2,"syntology":null},{"url":"/paper/lapt-label-driven-automated-prompt-tuning-for","slug":"lapt-label-driven-automated-prompt-tuning-for","title":"LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models","date":"2024-07-12","arxiv_id":"2407.08966","repositories_listed":2,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":2,"n_honours":2,"n_violates":2,"n_no_contract":5,"n_pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 2 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lapt-label-driven-automated-prompt-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2407.08966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08966"}},"official":{"repos":["ybzh/lapt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/paraphrase-types-elicit-prompt-engineering","slug":"paraphrase-types-elicit-prompt-engineering","title":"Paraphrase Types Elicit Prompt Engineering Capabilities","date":"2024-06-28","arxiv_id":"2406.19898","repositories_listed":2,"syntology":null},{"url":"/paper/understanding-sounds-missing-the-questions","slug":"understanding-sounds-missing-the-questions","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","date":"2024-06-12","arxiv_id":"2406.08402","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-worst-prompt-performance-of-large","slug":"on-the-worst-prompt-performance-of-large","title":"On the Worst Prompt Performance of Large Language Models","date":"2024-06-08","arxiv_id":"2406.10248","repositories_listed":2,"syntology":null},{"url":"/paper/optimizing-large-language-models-for-openapi","slug":"optimizing-large-language-models-for-openapi","title":"Optimizing Large Language Models for OpenAPI Code Completion","date":"2024-05-24","arxiv_id":"2405.15729","repositories_listed":2,"syntology":null},{"url":"/paper/can-we-use-large-language-models-to-fill","slug":"can-we-use-large-language-models-to-fill","title":"Can We Use Large Language Models to Fill Relevance Judgment Holes?","date":"2024-05-09","arxiv_id":"2405.05600","repositories_listed":2,"syntology":null},{"url":"/paper/semantic-routing-for-enhanced-performance-of","slug":"semantic-routing-for-enhanced-performance-of","title":"Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration","date":"2024-04-24","arxiv_id":"2404.15869","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semantic-routing-for-enhanced-performance-of#ran","syntology_url":"https://syntology.ai/paper/2404.15869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15869"}},"official":null}},{"url":"/paper/prism-a-promptable-and-robust-interactive","slug":"prism-a-promptable-and-robust-interactive","title":"PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts","date":"2024-04-23","arxiv_id":"2404.15028","repositories_listed":2,"syntology":null},{"url":"/paper/simple-techniques-for-enhancing-sentence","slug":"simple-techniques-for-enhancing-sentence","title":"Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models","date":"2024-04-05","arxiv_id":"2404.03921","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-models-powered-context-aware","slug":"large-language-models-powered-context-aware","title":"Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving","date":"2024-03-17","arxiv_id":"2403.11057","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-powered-context-aware#ran","syntology_url":"https://syntology.ai/paper/2403.11057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11057"}},"official":{"repos":["air-discover/llm-augmented-mtr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-llms-separate-instructions-from-data-and","slug":"can-llms-separate-instructions-from-data-and","title":"Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?","date":"2024-03-11","arxiv_id":"2403.06833","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-llms-separate-instructions-from-data-and#ran","syntology_url":"https://syntology.ai/paper/2403.06833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06833"}},"official":{"repos":["egozverev/shold-it-be-executed-or-processed"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-ecg-classification-with-multimodal","slug":"zero-shot-ecg-classification-with-multimodal","title":"Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement","date":"2024-03-11","arxiv_id":"2403.06659","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/zero-shot-ecg-classification-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.06659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06659"}},"official":{"repos":["cheliu-computation/merl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/language-agents-as-optimizable-graphs","slug":"language-agents-as-optimizable-graphs","title":"Language Agents as Optimizable Graphs","date":"2024-02-26","arxiv_id":"2402.16823","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-agents-as-optimizable-graphs#ran","syntology_url":"https://syntology.ai/paper/2402.16823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16823"}},"official":{"repos":["metauto-ai/gptswarm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/culturellm-incorporating-cultural-differences","slug":"culturellm-incorporating-cultural-differences","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","date":"2024-02-09","arxiv_id":"2402.10946","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/culturellm-incorporating-cultural-differences#ran","syntology_url":"https://syntology.ai/paper/2402.10946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10946"}},"official":{"repos":["scarelette/culturellm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-learning-for-extreme-multi-label","slug":"in-context-learning-for-extreme-multi-label","title":"In-Context Learning for Extreme Multi-Label Classification","date":"2024-01-22","arxiv_id":"2401.12178","repositories_listed":2,"syntology":null},{"url":"/paper/code-generation-with-alphacodium-from-prompt","slug":"code-generation-with-alphacodium-from-prompt","title":"Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering","date":"2024-01-16","arxiv_id":"2401.08500","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/code-generation-with-alphacodium-from-prompt#ran","syntology_url":"https://syntology.ai/paper/2401.08500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08500"}},"official":{"repos":["codium-ai/alphacodium"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-hierarchical-prompt-with-structured","slug":"learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","arxiv_id":"2312.06323","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-hierarchical-prompt-with-structured#ran","syntology_url":"https://syntology.ai/paper/2312.06323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06323"}},"official":{"repos":["vill-lab/2024-aaai-hpt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/can-generalist-foundation-models-outcompete","slug":"can-generalist-foundation-models-outcompete","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","date":"2023-11-28","arxiv_id":"2311.16452","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-generalist-foundation-models-outcompete#ran","syntology_url":"https://syntology.ai/paper/2311.16452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16452"}},"official":null}},{"url":"/paper/large-language-models-for-propaganda","slug":"large-language-models-for-propaganda","title":"Large Language Models for Propaganda Detection","date":"2023-10-10","arxiv_id":"2310.06422","repositories_listed":2,"syntology":null},{"url":"/paper/label-supervised-llama-finetuning","slug":"label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","repositories_listed":2,"syntology":null},{"url":"/paper/cot-bert-enhancing-unsupervised-sentence","slug":"cot-bert-enhancing-unsupervised-sentence","title":"CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-Thought","date":"2023-09-20","arxiv_id":"2309.11143","repositories_listed":2,"syntology":null},{"url":"/paper/pre-vision-language-prompt-learning-with","slug":"pre-vision-language-prompt-learning-with","title":"PRE: Vision-Language Prompt Learning with Reparameterization Encoder","date":"2023-09-14","arxiv_id":"2309.07760","repositories_listed":2,"syntology":null},{"url":"/paper/offline-prompt-evaluation-and-optimization","slug":"offline-prompt-evaluation-and-optimization","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","date":"2023-09-13","arxiv_id":"2309.06553","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/offline-prompt-evaluation-and-optimization#ran","syntology_url":"https://syntology.ai/paper/2309.06553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06553"}},"official":{"repos":["holarissun/prompt-oirl","vanderschaarlab/prompt-oirl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-the-efficacy-of-supervised","slug":"evaluating-the-efficacy-of-supervised","title":"Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media","date":"2023-09-07","arxiv_id":"2309.03564","repositories_listed":2,"syntology":null},{"url":"/paper/manipulating-embeddings-of-stable-diffusion","slug":"manipulating-embeddings-of-stable-diffusion","title":"Manipulating Embeddings of Stable Diffusion Prompts","date":"2023-08-23","arxiv_id":"2308.12059","repositories_listed":2,"syntology":null},{"url":"/paper/activation-addition-steering-language-models","slug":"activation-addition-steering-language-models","title":"Steering Language Models With Activation Engineering","date":"2023-08-20","arxiv_id":"2308.10248","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/activation-addition-steering-language-models#ran","syntology_url":"https://syntology.ai/paper/2308.10248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10248"}},"official":{"repos":["montemac/activation_additions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flows-building-blocks-of-reasoning-and","slug":"flows-building-blocks-of-reasoning-and","title":"Flows: Building Blocks of Reasoning and Collaborating AI","date":"2023-08-02","arxiv_id":"2308.01285","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flows-building-blocks-of-reasoning-and#ran","syntology_url":"https://syntology.ai/paper/2308.01285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01285"}},"official":{"repos":["epfl-dlab/aiflows","epfl-dlab/cc_flows"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-systematic-survey-of-prompt-engineering-on","slug":"a-systematic-survey-of-prompt-engineering-on","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","date":"2023-07-24","arxiv_id":"2307.12980","repositories_listed":2,"syntology":null},{"url":"/paper/self-regulating-prompts-foundational-model","slug":"self-regulating-prompts-foundational-model","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","date":"2023-07-13","arxiv_id":"2307.06948","repositories_listed":2,"syntology":{"n":21,"n_ran":17,"n_constructed":0,"n_ran_checked":12,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":3,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/self-regulating-prompts-foundational-model#ran","syntology_url":"https://syntology.ai/paper/2307.06948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06948"}},"official":{"repos":["muzairkhattak/promptsrc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/check-me-if-you-can-detecting-chatgpt","slug":"check-me-if-you-can-detecting-chatgpt","title":"On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing","date":"2023-06-07","arxiv_id":"2306.05524","repositories_listed":2,"syntology":null},{"url":"/paper/consistency-guided-prompt-learning-for-vision","slug":"consistency-guided-prompt-learning-for-vision","title":"Consistency-guided Prompt Learning for Vision-Language Models","date":"2023-06-01","arxiv_id":"2306.01195","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/consistency-guided-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2306.01195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01195"}},"official":{"repos":["shuvenduroy/coprompt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/jailbreaking-chatgpt-via-prompt-engineering","slug":"jailbreaking-chatgpt-via-prompt-engineering","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","date":"2023-05-23","arxiv_id":"2305.13860","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/jailbreaking-chatgpt-via-prompt-engineering#ran","syntology_url":"https://syntology.ai/paper/2305.13860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13860"}},"official":null}},{"url":"/paper/low-code-llm-visual-programming-over-llms","slug":"low-code-llm-visual-programming-over-llms","title":"Low-code LLM: Graphical User Interface over Large Language Models","date":"2023-04-17","arxiv_id":"2304.08103","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-evaluations-of-chatgpt-and-emotion","slug":"on-the-evaluations-of-chatgpt-and-emotion","title":"Towards Interpretable Mental Health Analysis with Large Language Models","date":"2023-04-06","arxiv_id":"2304.03347","repositories_listed":2,"syntology":null},{"url":"/paper/safety-analysis-in-the-era-of-large-language","slug":"safety-analysis-in-the-era-of-large-language","title":"Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT","date":"2023-04-03","arxiv_id":"2304.01246","repositories_listed":2,"syntology":null},{"url":"/paper/domain-specific-text-generation-for-machine","slug":"domain-specific-text-generation-for-machine","title":"Domain-Specific Text Generation for Machine Translation","date":"2022-08-11","arxiv_id":"2208.05909","repositories_listed":2,"syntology":null},{"url":"/paper/bigbio-a-framework-for-data-centric","slug":"bigbio-a-framework-for-data-centric","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","date":"2022-06-30","arxiv_id":"2206.15076","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bigbio-a-framework-for-data-centric#ran","syntology_url":"https://syntology.ai/paper/2206.15076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.15076"}},"official":{"repos":["bigscience-workshop/biomedical"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/decoupling-knowledge-from-memorization","slug":"decoupling-knowledge-from-memorization","title":"Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning","date":"2022-05-29","arxiv_id":"2205.14704","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/decoupling-knowledge-from-memorization#ran","syntology_url":"https://syntology.ai/paper/2205.14704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14704"}},"official":{"repos":["zjunlp/promptkg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/actionclip-a-new-paradigm-for-video-action","slug":"actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","arxiv_id":"2109.08472","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/actionclip-a-new-paradigm-for-video-action#ran","syntology_url":"https://syntology.ai/paper/2109.08472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08472"}},"official":{"repos":["sallymmx/actionclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/what-changes-can-large-scale-language-models","slug":"what-changes-can-large-scale-language-models","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","date":"2021-09-10","arxiv_id":"2109.04650","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/what-changes-can-large-scale-language-models#ran","syntology_url":"https://syntology.ai/paper/2109.04650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04650"}},"official":null}},{"url":"/paper/cutting-down-on-prompts-and-parameters-simple","slug":"cutting-down-on-prompts-and-parameters-simple","title":"Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models","date":"2021-06-24","arxiv_id":"2106.13353","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cutting-down-on-prompts-and-parameters-simple#ran","syntology_url":"https://syntology.ai/paper/2106.13353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13353"}},"official":{"repos":["ucinlp/null-prompts"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-tuning-and-prompt-engineering-of-llms","slug":"fine-tuning-and-prompt-engineering-of-llms","title":"Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges","date":"2025-06-25","arxiv_id":"2506.20598","repositories_listed":1,"syntology":null},{"url":"/paper/llm-as-a-fuzzy-judge-fine-tuning-large","slug":"llm-as-a-fuzzy-judge-fine-tuning-large","title":"LLM-as-a-Fuzzy-Judge: Fine-Tuning Large Language Models as a Clinical Evaluation Judge with Fuzzy Logic","date":"2025-06-12","arxiv_id":"2506.11221","repositories_listed":1,"syntology":null},{"url":"/paper/2506-10172","slug":"2506-10172","title":"A Navigation Framework Utilizing Vision-Language Models","date":"2025-06-11","arxiv_id":"2506.10172","repositories_listed":1,"syntology":null},{"url":"/paper/2506-08686","slug":"2506-08686","title":"Brevity is the soul of sustainability: Characterizing LLM response lengths","date":"2025-06-10","arxiv_id":"2506.08686","repositories_listed":1,"syntology":null},{"url":"/paper/towards-holistic-visual-quality-assessment-of","slug":"towards-holistic-visual-quality-assessment-of","title":"Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model","date":"2025-06-05","arxiv_id":"2506.04715","repositories_listed":1,"syntology":null},{"url":"/paper/bitbypass-a-new-direction-in-jailbreaking","slug":"bitbypass-a-new-direction-in-jailbreaking","title":"BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage","date":"2025-06-03","arxiv_id":"2506.02479","repositories_listed":1,"syntology":null},{"url":"/paper/auralsam2-enabling-sam2-hear-through-pyramid","slug":"auralsam2-enabling-sam2-hear-through-pyramid","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","date":"2025-06-01","arxiv_id":"2506.01015","repositories_listed":1,"syntology":null},{"url":"/paper/behavioral-augmentation-of-uml-class-diagrams","slug":"behavioral-augmentation-of-uml-class-diagrams","title":"Behavioral Augmentation of UML Class Diagrams: An Empirical Study of Large Language Models for Method Generation","date":"2025-06-01","arxiv_id":"2506.00788","repositories_listed":1,"syntology":null},{"url":"/paper/ml-agent-reinforcing-llm-agents-for","slug":"ml-agent-reinforcing-llm-agents-for","title":"ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering","date":"2025-05-29","arxiv_id":"2505.23723","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-augmented-generation-based-large-1","slug":"retrieval-augmented-generation-based-large-1","title":"Retrieval Augmented Generation based Large Language Models for Causality Mining","date":"2025-05-29","arxiv_id":"2505.23944","repositories_listed":1,"syntology":null},{"url":"/paper/a-course-correction-in-steerability","slug":"a-course-correction-in-steerability","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","date":"2025-05-27","arxiv_id":"2505.23816","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-ceiling-exploring-the-potential","slug":"breaking-the-ceiling-exploring-the-potential","title":"Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space","date":"2025-05-27","arxiv_id":"2505.21277","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/breaking-the-ceiling-exploring-the-potential#ran","syntology_url":"https://syntology.ai/paper/2505.21277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21277"}},"official":{"repos":["aries-iai/cl-gso"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/capability-based-scaling-laws-for-llm-red","slug":"capability-based-scaling-laws-for-llm-red","title":"Capability-Based Scaling Laws for LLM Red-Teaming","date":"2025-05-26","arxiv_id":"2505.20162","repositories_listed":1,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":0,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/capability-based-scaling-laws-for-llm-red#ran","syntology_url":"https://syntology.ai/paper/2505.20162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20162"}},"official":{"repos":["kotekjedi/capability-based-scaling"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-as-autonomous","slug":"large-language-models-as-autonomous","title":"Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program","date":"2025-05-26","arxiv_id":"2505.19896","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-prompt-engineering-robust-behavior","slug":"beyond-prompt-engineering-robust-behavior","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","date":"2025-05-23","arxiv_id":"2505.20322","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-prompt-engineering-robust-behavior#ran","syntology_url":"https://syntology.ai/paper/2505.20322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20322"}},"official":{"repos":["zjunlp/steer-target-atoms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rehabilitation-exercise-quality-assessment-1","slug":"rehabilitation-exercise-quality-assessment-1","title":"Rehabilitation Exercise Quality Assessment and Feedback Generation Using Large Language Models with Prompt Engineering","date":"2025-05-23","arxiv_id":"2505.18412","repositories_listed":1,"syntology":null},{"url":"/paper/prl-prompts-from-reinforcement-learning","slug":"prl-prompts-from-reinforcement-learning","title":"PRL: Prompts from Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14412","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-prompting-enhances-sentence","slug":"contrastive-prompting-enhances-sentence","title":"Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering","date":"2025-05-19","arxiv_id":"2505.12831","repositories_listed":1,"syntology":null},{"url":"/paper/halo-hierarchical-autonomous-logic-oriented","slug":"halo-hierarchical-autonomous-logic-oriented","title":"HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems","date":"2025-05-17","arxiv_id":"2505.13516","repositories_listed":1,"syntology":null},{"url":"/paper/tiny-qa-benchmark-ultra-lightweight-synthetic","slug":"tiny-qa-benchmark-ultra-lightweight-synthetic","title":"Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation","date":"2025-05-17","arxiv_id":"2505.12058","repositories_listed":1,"syntology":null},{"url":"/paper/mmrl-parameter-efficient-and-interaction","slug":"mmrl-parameter-efficient-and-interaction","title":"MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models","date":"2025-05-15","arxiv_id":"2505.10088","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-suffix-filtering-a-defense","slug":"adversarial-suffix-filtering-a-defense","title":"Adversarial Suffix Filtering: a Defense Pipeline for LLMs","date":"2025-05-14","arxiv_id":"2505.09602","repositories_listed":1,"syntology":null},{"url":"/paper/layered-unlearning-for-adversarial-relearning","slug":"layered-unlearning-for-adversarial-relearning","title":"Layered Unlearning for Adversarial Relearning","date":"2025-05-14","arxiv_id":"2505.09500","repositories_listed":1,"syntology":null},{"url":"/paper/concept-level-explainability-for-auditing","slug":"concept-level-explainability-for-auditing","title":"Concept-Level Explainability for Auditing & Steering LLM Responses","date":"2025-05-12","arxiv_id":"2505.07610","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/concept-level-explainability-for-auditing#ran","syntology_url":"https://syntology.ai/paper/2505.07610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07610"}},"official":{"repos":["k-amara/ConceptX"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/symbolic-regression-with-multimodal-large","slug":"symbolic-regression-with-multimodal-large","title":"Symbolic Regression with Multimodal Large Language Models and Kolmogorov Arnold Networks","date":"2025-05-12","arxiv_id":"2505.07956","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-vision-language-action-models-in","slug":"benchmarking-vision-language-action-models-in","title":"Benchmarking Vision, Language, & Action Models in Procedurally Generated, Open Ended Action Environments","date":"2025-05-08","arxiv_id":"2505.05540","repositories_listed":1,"syntology":null},{"url":"/paper/show-or-tell-a-benchmark-to-evaluate-visual","slug":"show-or-tell-a-benchmark-to-evaluate-visual","title":"Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation","date":"2025-05-06","arxiv_id":"2505.06280","repositories_listed":1,"syntology":null},{"url":"/paper/autolibra-agent-metric-induction-from-open","slug":"autolibra-agent-metric-induction-from-open","title":"AutoLibra: Agent Metric Induction from Open-Ended Feedback","date":"2025-05-05","arxiv_id":"2505.02820","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-contrastive-feedback-for-effective","slug":"evaluating-contrastive-feedback-for-effective","title":"Evaluating Contrastive Feedback for Effective User Simulations","date":"2025-05-05","arxiv_id":"2505.02560","repositories_listed":1,"syntology":null},{"url":"/paper/towards-artificial-intelligence-research","slug":"towards-artificial-intelligence-research","title":"Towards Artificial Intelligence Research Assistant for Expert-Involved Learning","date":"2025-05-03","arxiv_id":"2505.04638","repositories_listed":1,"syntology":null},{"url":"/paper/ensuring-reproducibility-in-generative-ai","slug":"ensuring-reproducibility-in-generative-ai","title":"Ensuring Reproducibility in Generative AI Systems for General Use Cases: A Framework for Regression Testing and Open Datasets","date":"2025-05-02","arxiv_id":"2505.02854","repositories_listed":1,"syntology":null},{"url":"/paper/toward-evaluative-thinking-meta-policy","slug":"toward-evaluative-thinking-meta-policy","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","date":"2025-04-28","arxiv_id":"2504.20157","repositories_listed":1,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":15,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/toward-evaluative-thinking-meta-policy#ran","syntology_url":"https://syntology.ai/paper/2504.20157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.20157"}},"official":{"repos":["minnesotanlp/mpo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-on-prompt-compression-for","slug":"an-empirical-study-on-prompt-compression-for","title":"An Empirical Study on Prompt Compression for Large Language Models","date":"2025-04-24","arxiv_id":"2505.00019","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-empirical-study-on-prompt-compression-for#ran","syntology_url":"https://syntology.ai/paper/2505.00019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00019"}},"official":{"repos":["3DAgentWorld/Toolkit-for-Prompt-Compression"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/private-federated-learning-using-preference","slug":"private-federated-learning-using-preference","title":"Private Federated Learning using Preference-Optimized Synthetic Data","date":"2025-04-23","arxiv_id":"2504.16438","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/private-federated-learning-using-preference#ran","syntology_url":"https://syntology.ai/paper/2504.16438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.16438"}},"official":{"repos":["meiyuw/popri"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/what-s-the-difference-supporting-users-in","slug":"what-s-the-difference-supporting-users-in","title":"What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns","date":"2025-04-22","arxiv_id":"2504.15815","repositories_listed":1,"syntology":null},{"url":"/paper/generative-ai-act-ii-test-time-scaling-drives","slug":"generative-ai-act-ii-test-time-scaling-drives","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","date":"2025-04-18","arxiv_id":"2504.13828","repositories_listed":1,"syntology":null},{"url":"/paper/search-is-all-you-need-for-few-shot-anomaly","slug":"search-is-all-you-need-for-few-shot-anomaly","title":"Search is All You Need for Few-shot Anomaly Detection","date":"2025-04-16","arxiv_id":"2504.11895","repositories_listed":1,"syntology":null}],"syntology_records":42,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":143,"papers_where_code_ran_first_page":"/task/prompt-engineering/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":13,"url":"/task/prompt-engineering/papers/2","json":"/task/prompt-engineering/papers/2.json","rows":100},{"order":"archive","page":3,"of":13,"url":"/task/prompt-engineering/papers/3","json":"/task/prompt-engineering/papers/3.json","rows":100},{"order":"archive","page":4,"of":13,"url":"/task/prompt-engineering/papers/4","json":"/task/prompt-engineering/papers/4.json","rows":100},{"order":"archive","page":5,"of":13,"url":"/task/prompt-engineering/papers/5","json":"/task/prompt-engineering/papers/5.json","rows":100},{"order":"archive","page":6,"of":13,"url":"/task/prompt-engineering/papers/6","json":"/task/prompt-engineering/papers/6.json","rows":100},{"order":"archive","page":7,"of":13,"url":"/task/prompt-engineering/papers/7","json":"/task/prompt-engineering/papers/7.json","rows":100},{"order":"archive","page":8,"of":13,"url":"/task/prompt-engineering/papers/8","json":"/task/prompt-engineering/papers/8.json","rows":100},{"order":"archive","page":9,"of":13,"url":"/task/prompt-engineering/papers/9","json":"/task/prompt-engineering/papers/9.json","rows":100},{"order":"archive","page":10,"of":13,"url":"/task/prompt-engineering/papers/10","json":"/task/prompt-engineering/papers/10.json","rows":100},{"order":"archive","page":11,"of":13,"url":"/task/prompt-engineering/papers/11","json":"/task/prompt-engineering/papers/11.json","rows":100},{"order":"archive","page":12,"of":13,"url":"/task/prompt-engineering/papers/12","json":"/task/prompt-engineering/papers/12.json","rows":100},{"order":"archive","page":13,"of":13,"url":"/task/prompt-engineering/papers/13","json":"/task/prompt-engineering/papers/13.json","rows":36},{"order":"ran","page":1,"of":2,"url":"/task/prompt-engineering/papers/ran/1","json":"/task/prompt-engineering/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/prompt-engineering/papers/ran/2","json":"/task/prompt-engineering/papers/ran/2.json","rows":43}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"ecfa8c83ae09bbc72ee772d898e2d0a019eed7e54c96234f92db3fc9a6b3a226","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}