{"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/general-knowledge","name":"General Knowledge","slug":"general-knowledge","description_markdown":"This task aims to evaluate the ability of a model to answer general-knowledge questions.\r\n\r\nSource: [BIG-bench](https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/general_knowledge)","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":399,"papers_with_code":173,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":2,"subtasks":7,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/general-knowledge-on-big-bench","slug":"general-knowledge-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla-70B (few-shot, k=5)","paper_title":"Training Compute-Optimal Large Language Models","paper_url":"/paper/training-compute-optimal-large-language","paper_date":"2022-03-29","arxiv_id":"2203.15556","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349},{"url":"/dataset/bear-big","name":"BEAR-probe","full_name":"Benchmark for Evaluating Associative Reasoning","num_papers_in_archive":1}],"subtasks":[{"url":"/task/global-facts","name":"Global Facts"},{"url":"/task/miscellaneous","name":"Miscellaneous"},{"url":"/task/movie-recommendation","name":"Movie Recommendation"},{"url":"/task/natural-questions","name":"Natural Questions"},{"url":"/task/similarities-abstraction","name":"Similarities Abstraction"},{"url":"/task/sports-understanding","name":"Sports Understanding"},{"url":"/task/triviaqa","name":"TriviaQA"}],"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":4,"rows_per_page":100,"shown":100,"of":399,"of_with_code":173,"tagged_in_all":399,"counts":{"archive_papers_tagged":399,"with_a_code_link":173,"where_syntology_ran_a_sample":59,"not_listed_spam_title":0,"listed":399,"listed_where_code_ran":59,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":50,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":50,"listed_every_run_a_failure_of_syntologys_instrument":9,"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/joey-nmt-a-minimalist-nmt-toolkit-for-novices","slug":"joey-nmt-a-minimalist-nmt-toolkit-for-novices","title":"Joey NMT: A Minimalist NMT Toolkit for Novices","date":"2019-07-29","arxiv_id":"1907.12484","repositories_listed":8,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":13,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/joey-nmt-a-minimalist-nmt-toolkit-for-novices#ran","syntology_url":"https://syntology.ai/paper/1907.12484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12484"}},"official":{"repos":["joeynmt/joeynmt"],"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/conceptnet-55-an-open-multilingual-graph-of","slug":"conceptnet-55-an-open-multilingual-graph-of","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","date":"2016-12-12","arxiv_id":"1612.03975","repositories_listed":6,"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":2,"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/conceptnet-55-an-open-multilingual-graph-of#ran","syntology_url":"https://syntology.ai/paper/1612.03975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.03975"}},"official":{"repos":["commonsense/conceptnet-numberbatch"],"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/automated-phrase-mining-from-massive-text","slug":"automated-phrase-mining-from-massive-text","title":"Automated Phrase Mining from Massive Text Corpora","date":"2017-02-15","arxiv_id":"1702.04457","repositories_listed":4,"syntology":null},{"url":"/paper/time-travelling-pixels-bitemporal-features","slug":"time-travelling-pixels-bitemporal-features","title":"Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection","date":"2023-12-23","arxiv_id":"2312.16202","repositories_listed":3,"syntology":null},{"url":"/paper/explanations-as-features-llm-based-features","slug":"explanations-as-features-llm-based-features","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","date":"2023-05-31","arxiv_id":"2305.19523","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explanations-as-features-llm-based-features#ran","syntology_url":"https://syntology.ai/paper/2305.19523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19523"}},"official":{"repos":["XiaoxinHe/TAPE","xiaoxinhe/tape_arxiv_2023"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-understand-phrases-by-embedding","slug":"learning-to-understand-phrases-by-embedding","title":"Learning to Understand Phrases by Embedding the Dictionary","date":"2015-04-02","arxiv_id":"1504.00548","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/learning-to-understand-phrases-by-embedding#ran","syntology_url":"https://syntology.ai/paper/1504.00548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1504.00548"}},"official":null}},{"url":"/paper/survey-on-abstractive-text-summarization","slug":"survey-on-abstractive-text-summarization","title":"Survey on Abstractive Text Summarization: Dataset, Models, and Metrics","date":"2024-12-22","arxiv_id":"2412.17165","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/cascade-prompt-learning-for-vision-language","slug":"cascade-prompt-learning-for-vision-language","title":"Cascade Prompt Learning for Vision-Language Model Adaptation","date":"2024-09-26","arxiv_id":"2409.17805","repositories_listed":2,"syntology":null},{"url":"/paper/domainrag-a-chinese-benchmark-for-evaluating","slug":"domainrag-a-chinese-benchmark-for-evaluating","title":"DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05654","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"12 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/domainrag-a-chinese-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2406.05654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05654"}},"official":{"repos":["ShootingWong/DomainRAG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/f-lmm-grounding-frozen-large-multimodal","slug":"f-lmm-grounding-frozen-large-multimodal","title":"F-LMM: Grounding Frozen Large Multimodal Models","date":"2024-06-09","arxiv_id":"2406.05821","repositories_listed":2,"syntology":null},{"url":"/paper/a-new-learning-paradigm-for-foundation-model","slug":"a-new-learning-paradigm-for-foundation-model","title":"A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detection","date":"2023-12-02","arxiv_id":"2312.01163","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-the-potential-of-large-language-1","slug":"exploring-the-potential-of-large-language-1","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","date":"2023-07-07","arxiv_id":"2307.03393","repositories_listed":2,"syntology":null},{"url":"/paper/bert4cmr-cross-market-recommendation-with","slug":"bert4cmr-cross-market-recommendation-with","title":"Bert4XMR: Cross-Market Recommendation with Bidirectional Encoder Representations from Transformer","date":"2023-05-24","arxiv_id":"2305.15145","repositories_listed":2,"syntology":null},{"url":"/paper/continual-learning-of-language-models","slug":"continual-learning-of-language-models","title":"Continual Pre-training of Language Models","date":"2023-02-07","arxiv_id":"2302.03241","repositories_listed":2,"syntology":null},{"url":"/paper/adapting-a-language-model-while-preserving","slug":"adapting-a-language-model-while-preserving","title":"Adapting a Language Model While Preserving its General Knowledge","date":"2023-01-21","arxiv_id":"2301.08986","repositories_listed":2,"syntology":null},{"url":"/paper/knowledge-distillation-for-detection","slug":"knowledge-distillation-for-detection","title":"Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","date":"2022-11-15","arxiv_id":"2211.08071","repositories_listed":2,"syntology":null},{"url":"/paper/cc-riddle-a-question-answering-dataset-of","slug":"cc-riddle-a-question-answering-dataset-of","title":"CC-Riddle: A Question Answering Dataset of Chinese Character Riddles","date":"2022-06-28","arxiv_id":"2206.13778","repositories_listed":2,"syntology":null},{"url":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/beametrics-a-benchmark-for-language","slug":"beametrics-a-benchmark-for-language","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","date":"2021-10-18","arxiv_id":"2110.09147","repositories_listed":2,"syntology":null},{"url":"/paper/exploiting-adapters-for-cross-lingual-low","slug":"exploiting-adapters-for-cross-lingual-low","title":"Exploiting Adapters for Cross-lingual Low-resource Speech Recognition","date":"2021-05-18","arxiv_id":"2105.11905","repositories_listed":2,"syntology":null},{"url":"/paper/transformers-as-soft-reasoners-over-language","slug":"transformers-as-soft-reasoners-over-language","title":"Transformers as Soft Reasoners over Language","date":"2020-02-14","arxiv_id":"2002.05867","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/transformers-as-soft-reasoners-over-language#ran","syntology_url":"https://syntology.ai/paper/2002.05867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05867"}},"official":null}},{"url":"/paper/what-does-my-qa-model-know-devising","slug":"what-does-my-qa-model-know-devising","title":"What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge","date":"2019-12-31","arxiv_id":"1912.13337","repositories_listed":2,"syntology":null},{"url":"/paper/go-from-the-general-to-the-particular-multi","slug":"go-from-the-general-to-the-particular-multi","title":"Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks","date":"2019-11-22","arxiv_id":"1911.09912","repositories_listed":2,"syntology":null},{"url":"/paper/integrating-semantic-knowledge-to-tackle-zero","slug":"integrating-semantic-knowledge-to-tackle-zero","title":"Integrating Semantic Knowledge to Tackle Zero-shot Text Classification","date":"2019-03-29","arxiv_id":"1903.12626","repositories_listed":2,"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/integrating-semantic-knowledge-to-tackle-zero#ran","syntology_url":"https://syntology.ai/paper/1903.12626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.12626"}},"official":{"repos":["JingqingZ/KG4ZeroShotText"],"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/yuanfudao-at-semeval-2018-task-11-three-way","slug":"yuanfudao-at-semeval-2018-task-11-three-way","title":"Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension","date":"2018-03-01","arxiv_id":"1803.00191","repositories_listed":2,"syntology":null},{"url":"/paper/conceptnet-at-semeval-2017-task-2-extending","slug":"conceptnet-at-semeval-2017-task-2-extending","title":"ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge","date":"2017-04-11","arxiv_id":"1704.03560","repositories_listed":2,"syntology":null},{"url":"/paper/unveiling-causal-reasoning-in-large-language","slug":"unveiling-causal-reasoning-in-large-language","title":"Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?","date":"2025-06-26","arxiv_id":"2506.21215","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_honours":3,"n_violates":3,"n_no_contract":0,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 3 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unveiling-causal-reasoning-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2506.21215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.21215"}},"official":{"repos":["haoang97/causalprobe-2024"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/taxoadapt-aligning-llm-based-multidimensional","slug":"taxoadapt-aligning-llm-based-multidimensional","title":"TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora","date":"2025-06-12","arxiv_id":"2506.10737","repositories_listed":1,"syntology":null},{"url":"/paper/improving-personalized-search-with-1","slug":"improving-personalized-search-with-1","title":"Improving Personalized Search with Regularized Low-Rank Parameter Updates","date":"2025-06-11","arxiv_id":"2506.10182","repositories_listed":1,"syntology":null},{"url":"/paper/hssbench-benchmarking-humanities-and-social","slug":"hssbench-benchmarking-humanities-and-social","title":"HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models","date":"2025-06-04","arxiv_id":"2506.03922","repositories_listed":1,"syntology":null},{"url":"/paper/helm-hyperbolic-large-language-models-via","slug":"helm-hyperbolic-large-language-models-via","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","date":"2025-05-30","arxiv_id":"2505.24722","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/helm-hyperbolic-large-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2505.24722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24722"}},"official":{"repos":["graph-and-geometric-learning/helm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/bnmmlu-measuring-massive-multitask-language","slug":"bnmmlu-measuring-massive-multitask-language","title":"BnMMLU: Measuring Massive Multitask Language Understanding in Bengali","date":"2025-05-25","arxiv_id":"2505.18951","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-knowledge-injection-framework-for-1","slug":"a-general-knowledge-injection-framework-for-1","title":"A General Knowledge Injection Framework for ICD Coding","date":"2025-05-24","arxiv_id":"2505.18708","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10939","slug":"2505-10939","title":"GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge Subtraction","date":"2025-05-16","arxiv_id":"2505.10939","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/from-knowledge-to-reasoning-evaluating-llms","slug":"from-knowledge-to-reasoning-evaluating-llms","title":"From Knowledge to Reasoning: Evaluating LLMs for Ionic Liquids Research in Chemical and Biological Engineering","date":"2025-05-11","arxiv_id":"2505.06964","repositories_listed":1,"syntology":null},{"url":"/paper/a-dual-space-framework-for-general-knowledge","slug":"a-dual-space-framework-for-general-knowledge","title":"A Dual-Space Framework for General Knowledge Distillation of Large Language Models","date":"2025-04-15","arxiv_id":"2504.11426","repositories_listed":1,"syntology":null},{"url":"/paper/planning-safety-trajectories-with-dual-phase","slug":"planning-safety-trajectories-with-dual-phase","title":"Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language Models","date":"2025-04-06","arxiv_id":"2504.04562","repositories_listed":1,"syntology":null},{"url":"/paper/effective-skill-unlearning-through","slug":"effective-skill-unlearning-through","title":"Effective Skill Unlearning through Intervention and Abstention","date":"2025-03-27","arxiv_id":"2503.21730","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":1,"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/effective-skill-unlearning-through#ran","syntology_url":"https://syntology.ai/paper/2503.21730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21730"}},"official":{"repos":["trustworthy-ml-lab/effective_skill_unlearning"],"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/distilling-stereo-networks-for-performant-and","slug":"distilling-stereo-networks-for-performant-and","title":"Distilling Stereo Networks for Performant and Efficient Leaner Networks","date":"2025-03-24","arxiv_id":"2503.18544","repositories_listed":1,"syntology":null},{"url":"/paper/how-robust-are-router-llms-analysis-of-the","slug":"how-robust-are-router-llms-analysis-of-the","title":"How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities","date":"2025-03-20","arxiv_id":"2504.07113","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-fine-tuning-from-pre-training","slug":"disentangling-fine-tuning-from-pre-training","title":"Disentangling Fine-Tuning from Pre-Training in Visual Captioning with Hybrid Markov Logic","date":"2025-03-18","arxiv_id":"2503.13847","repositories_listed":1,"syntology":null},{"url":"/paper/foundation-x-integrating-classification","slug":"foundation-x-integrating-classification","title":"Foundation X: Integrating Classification, Localization, and Segmentation through Lock-Release Pretraining Strategy for Chest X-ray Analysis","date":"2025-03-12","arxiv_id":"2503.09860","repositories_listed":1,"syntology":null},{"url":"/paper/fusechat-3-0-preference-optimization-meets","slug":"fusechat-3-0-preference-optimization-meets","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","date":"2025-03-06","arxiv_id":"2503.04222","repositories_listed":1,"syntology":null},{"url":"/paper/keeping-yourself-is-important-in-downstream","slug":"keeping-yourself-is-important-in-downstream","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","date":"2025-03-06","arxiv_id":"2503.04543","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-personalized-large-language","slug":"a-survey-of-personalized-large-language","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","date":"2025-02-17","arxiv_id":"2502.11528","repositories_listed":1,"syntology":null},{"url":"/paper/long-vita-scaling-large-multi-modal-models-to","slug":"long-vita-scaling-large-multi-modal-models-to","title":"Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray","date":"2025-02-07","arxiv_id":"2502.05177","repositories_listed":1,"syntology":null},{"url":"/paper/phd-knowledge-not-required-a-reasoning","slug":"phd-knowledge-not-required-a-reasoning","title":"PhD Knowledge Not Required: A Reasoning Challenge for Large Language Models","date":"2025-02-03","arxiv_id":"2502.01584","repositories_listed":1,"syntology":null},{"url":"/paper/dagprompt-pushing-the-limits-of-graph","slug":"dagprompt-pushing-the-limits-of-graph","title":"DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach","date":"2025-01-25","arxiv_id":"2501.15142","repositories_listed":1,"syntology":null},{"url":"/paper/the-breeze-2-herd-of-models-traditional","slug":"the-breeze-2-herd-of-models-traditional","title":"The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities","date":"2025-01-23","arxiv_id":"2501.13921","repositories_listed":1,"syntology":null},{"url":"/paper/super-class-guided-transformer-for-zero-shot","slug":"super-class-guided-transformer-for-zero-shot","title":"Super-class guided Transformer for Zero-Shot Attribute Classification","date":"2025-01-10","arxiv_id":"2501.05728","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/super-class-guided-transformer-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2501.05728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.05728"}},"official":{"repos":["mlvlab/SugaFormer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/are-vlms-ready-for-autonomous-driving-an","slug":"are-vlms-ready-for-autonomous-driving-an","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","date":"2025-01-07","arxiv_id":"2501.04003","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/are-vlms-ready-for-autonomous-driving-an#ran","syntology_url":"https://syntology.ai/paper/2501.04003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04003"}},"official":{"repos":["opendrivelab/drivelm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rag-with-differential-privacy","slug":"rag-with-differential-privacy","title":"RAG with Differential Privacy","date":"2024-12-26","arxiv_id":"2412.19291","repositories_listed":1,"syntology":null},{"url":"/paper/llm-rg4-flexible-and-factual-radiology-report","slug":"llm-rg4-flexible-and-factual-radiology-report","title":"LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts","date":"2024-12-16","arxiv_id":"2412.12001","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-cryptic-crosswords-challenging-for","slug":"what-makes-cryptic-crosswords-challenging-for","title":"What Makes Cryptic Crosswords Challenging for LLMs?","date":"2024-12-12","arxiv_id":"2412.09012","repositories_listed":1,"syntology":null},{"url":"/paper/same-learning-generic-language-guided-visual","slug":"same-learning-generic-language-guided-visual","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","date":"2024-12-07","arxiv_id":"2412.05552","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-transfer-learning-for-video","slug":"efficient-transfer-learning-for-video","title":"Efficient Transfer Learning for Video-language Foundation Models","date":"2024-11-18","arxiv_id":"2411.11223","repositories_listed":1,"syntology":null},{"url":"/paper/mm-eval-a-hierarchical-benchmark-for-modern","slug":"mm-eval-a-hierarchical-benchmark-for-modern","title":"MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs","date":"2024-11-14","arxiv_id":"2411.09492","repositories_listed":1,"syntology":null},{"url":"/paper/safe-slow-and-fast-parameter-efficient-tuning","slug":"safe-slow-and-fast-parameter-efficient-tuning","title":"SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models","date":"2024-11-04","arxiv_id":"2411.02175","repositories_listed":1,"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/safe-slow-and-fast-parameter-efficient-tuning#ran","syntology_url":"https://syntology.ai/paper/2411.02175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02175"}},"official":{"repos":["MIFA-Lab/SAFE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/point-prc-a-prompt-learning-based-regulation","slug":"point-prc-a-prompt-learning-based-regulation","title":"Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis","date":"2024-10-27","arxiv_id":"2410.20406","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/point-prc-a-prompt-learning-based-regulation#ran","syntology_url":"https://syntology.ai/paper/2410.20406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20406"}},"official":{"repos":["auniquesun/point-prc"],"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":["official"]}}},{"url":"/paper/should-we-really-edit-language-models-on-the","slug":"should-we-really-edit-language-models-on-the","title":"Should We Really Edit Language Models? On the Evaluation of Edited Language Models","date":"2024-10-24","arxiv_id":"2410.18785","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/should-we-really-edit-language-models-on-the#ran","syntology_url":"https://syntology.ai/paper/2410.18785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18785"}},"official":{"repos":["lqinfdim/editingevaluation"],"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":["found_in_text","official"]}}},{"url":"/paper/voicebench-benchmarking-llm-based-voice","slug":"voicebench-benchmarking-llm-based-voice","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","date":"2024-10-22","arxiv_id":"2410.17196","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/voicebench-benchmarking-llm-based-voice#ran","syntology_url":"https://syntology.ai/paper/2410.17196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17196"}},"official":{"repos":["matthewcym/voicebench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/manet-fine-tuning-segment-anything-model-for","slug":"manet-fine-tuning-segment-anything-model-for","title":"MANet: Fine-Tuning Segment Anything Model for Multimodal Remote Sensing Semantic Segmentation","date":"2024-10-15","arxiv_id":"2410.11160","repositories_listed":1,"syntology":null},{"url":"/paper/distribution-aware-noisy-label-crack","slug":"distribution-aware-noisy-label-crack","title":"Distribution-aware Noisy-label Crack Segmentation","date":"2024-10-12","arxiv_id":"2410.09409","repositories_listed":1,"syntology":null},{"url":"/paper/da-ada-learning-domain-aware-adapter-for","slug":"da-ada-learning-domain-aware-adapter-for","title":"DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection","date":"2024-10-11","arxiv_id":"2410.09004","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/da-ada-learning-domain-aware-adapter-for#ran","syntology_url":"https://syntology.ai/paper/2410.09004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09004"}},"official":{"repos":["therock90421/da-ada"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/parameter-efficient-fine-tuning-in-spectral","slug":"parameter-efficient-fine-tuning-in-spectral","title":"Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning","date":"2024-10-10","arxiv_id":"2410.08114","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":6,"n_instrument":7,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/parameter-efficient-fine-tuning-in-spectral#ran","syntology_url":"https://syntology.ai/paper/2410.08114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08114"}},"official":{"repos":["jerryfeng2003/pointgst"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-aggregation-for-low-rank-adaptation","slug":"selective-aggregation-for-low-rank-adaptation","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","date":"2024-10-02","arxiv_id":"2410.01463","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selective-aggregation-for-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2410.01463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01463"}},"official":{"repos":["Pengxin-Guo/FedSA-LoRA"],"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/e2map-experience-and-emotion-map-for-self","slug":"e2map-experience-and-emotion-map-for-self","title":"E2Map: Experience-and-Emotion Map for Self-Reflective Robot Navigation with Language Models","date":"2024-09-16","arxiv_id":"2409.10027","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-medical-images-with-general","slug":"aligning-medical-images-with-general","title":"Aligning Medical Images with General Knowledge from Large Language Models","date":"2024-08-31","arxiv_id":"2409.00341","repositories_listed":1,"syntology":null},{"url":"/paper/how-far-can-cantonese-nlp-go-benchmarking","slug":"how-far-can-cantonese-nlp-go-benchmarking","title":"How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models","date":"2024-08-29","arxiv_id":"2408.16756","repositories_listed":1,"syntology":null},{"url":"/paper/diagen-diverse-image-augmentation-with","slug":"diagen-diverse-image-augmentation-with","title":"DIAGen: Diverse Image Augmentation with Generative Models","date":"2024-08-26","arxiv_id":"2408.14584","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diagen-diverse-image-augmentation-with#ran","syntology_url":"https://syntology.ai/paper/2408.14584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14584"}},"official":{"repos":["visinf/diagen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/molecular-graph-representation-learning","slug":"molecular-graph-representation-learning","title":"Molecular Graph Representation Learning Integrating Large Language Models with Domain-specific Small Models","date":"2024-08-19","arxiv_id":"2408.10124","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01262","slug":"2408-01262","title":"RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework","date":"2024-08-02","arxiv_id":"2408.01262","repositories_listed":1,"syntology":null},{"url":"/paper/safetywashing-do-ai-safety-benchmarks","slug":"safetywashing-do-ai-safety-benchmarks","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","date":"2024-07-31","arxiv_id":"2407.21792","repositories_listed":1,"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/safetywashing-do-ai-safety-benchmarks#ran","syntology_url":"https://syntology.ai/paper/2407.21792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21792"}},"official":{"repos":["centerforaisafety/safetywashing"],"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":["official"]}}},{"url":"/paper/can-editing-llms-inject-harm","slug":"can-editing-llms-inject-harm","title":"Can Editing LLMs Inject Harm?","date":"2024-07-29","arxiv_id":"2407.20224","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"10 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-editing-llms-inject-harm#ran","syntology_url":"https://syntology.ai/paper/2407.20224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20224"}},"official":null}},{"url":"/paper/prior-knowledge-integration-via-llm-encoding","slug":"prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","arxiv_id":"2407.15051","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prior-knowledge-integration-via-llm-encoding#ran","syntology_url":"https://syntology.ai/paper/2407.15051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15051"}},"official":{"repos":["fletcherjiang/llmepet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/quantized-prompt-for-efficient-generalization","slug":"quantized-prompt-for-efficient-generalization","title":"Quantized Prompt for Efficient Generalization of Vision-Language Models","date":"2024-07-15","arxiv_id":"2407.10704","repositories_listed":1,"syntology":null},{"url":"/paper/elecbench-a-power-dispatch-evaluation","slug":"elecbench-a-power-dispatch-evaluation","title":"ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models","date":"2024-07-07","arxiv_id":"2407.05365","repositories_listed":1,"syntology":null},{"url":"/paper/me-myself-and-ai-the-situational-awareness","slug":"me-myself-and-ai-the-situational-awareness","title":"Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs","date":"2024-07-05","arxiv_id":"2407.04694","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/me-myself-and-ai-the-situational-awareness#ran","syntology_url":"https://syntology.ai/paper/2407.04694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04694"}},"official":{"repos":["lrudl/sad"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/to-forget-or-not-towards-practical-knowledge","slug":"to-forget-or-not-towards-practical-knowledge","title":"To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models","date":"2024-07-02","arxiv_id":"2407.01920","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/to-forget-or-not-towards-practical-knowledge#ran","syntology_url":"https://syntology.ai/paper/2407.01920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01920"}},"official":{"repos":["zjunlp/knowundo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/decoupling-general-and-personalized-knowledge","slug":"decoupling-general-and-personalized-knowledge","title":"Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition","date":"2024-06-28","arxiv_id":"2406.19931","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/decoupling-general-and-personalized-knowledge#ran","syntology_url":"https://syntology.ai/paper/2406.19931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19931"}},"official":{"repos":["xinghaowu/feddecomp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/citybench-evaluating-the-capabilities-of","slug":"citybench-evaluating-the-capabilities-of","title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","date":"2024-06-20","arxiv_id":"2406.13945","repositories_listed":1,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":6,"n_honours":4,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/citybench-evaluating-the-capabilities-of#ran","syntology_url":"https://syntology.ai/paper/2406.13945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13945"}},"official":{"repos":["tsinghua-fib-lab/citybench"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/are-large-language-models-a-good-replacement","slug":"are-large-language-models-a-good-replacement","title":"Are Large Language Models a Good Replacement of Taxonomies?","date":"2024-06-17","arxiv_id":"2406.11131","repositories_listed":1,"syntology":null},{"url":"/paper/repliqa-a-question-answering-dataset-for","slug":"repliqa-a-question-answering-dataset-for","title":"RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content","date":"2024-06-17","arxiv_id":"2406.11811","repositories_listed":1,"syntology":null},{"url":"/paper/avoiding-copyright-infringement-via-machine","slug":"avoiding-copyright-infringement-via-machine","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","date":"2024-06-16","arxiv_id":"2406.10952","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/avoiding-copyright-infringement-via-machine#ran","syntology_url":"https://syntology.ai/paper/2406.10952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10952"}},"official":{"repos":["guangyaodou/SSU_Unlearn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rad-a-comprehensive-dataset-for-benchmarking","slug":"rad-a-comprehensive-dataset-for-benchmarking","title":"RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection","date":"2024-06-11","arxiv_id":"2406.07176","repositories_listed":1,"syntology":null},{"url":"/paper/hydra-model-factorization-framework-for-black","slug":"hydra-model-factorization-framework-for-black","title":"HYDRA: Model Factorization Framework for Black-Box LLM Personalization","date":"2024-06-05","arxiv_id":"2406.02888","repositories_listed":1,"syntology":{"n":16,"n_ran":16,"n_constructed":2,"n_ran_checked":4,"n_instrument":12,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":16,"phrase":"16 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hydra-model-factorization-framework-for-black#ran","syntology_url":"https://syntology.ai/paper/2406.02888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02888"}},"official":{"repos":["night-chen/hydra"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/contextflow-generalist-specialist-flow-based","slug":"contextflow-generalist-specialist-flow-based","title":"ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding","date":"2024-06-02","arxiv_id":"2406.00578","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contextflow-generalist-specialist-flow-based#ran","syntology_url":"https://syntology.ai/paper/2406.00578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00578"}},"official":{"repos":["gudovskiy/contextflow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/slow-and-steady-wins-the-race-maintaining","slug":"slow-and-steady-wins-the-race-maintaining","title":"Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks","date":"2024-06-01","arxiv_id":"2406.02596","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/slow-and-steady-wins-the-race-maintaining#ran","syntology_url":"https://syntology.ai/paper/2406.02596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02596"}},"official":{"repos":["dojeon-ai/hare-tortoise"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/croft-robust-fine-tuning-with-concurrent","slug":"croft-robust-fine-tuning-with-concurrent","title":"CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection","date":"2024-05-26","arxiv_id":"2405.16417","repositories_listed":1,"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/croft-robust-fine-tuning-with-concurrent#ran","syntology_url":"https://syntology.ai/paper/2405.16417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16417"}},"official":{"repos":["linllll/croft"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/health-index-estimation-through-integration","slug":"health-index-estimation-through-integration","title":"Health Index Estimation Through Integration of General Knowledge with Unsupervised Learning","date":"2024-05-08","arxiv_id":"2405.04990","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-graphs-for-empirical-concept","slug":"knowledge-graphs-for-empirical-concept","title":"Knowledge graphs for empirical concept retrieval","date":"2024-04-10","arxiv_id":"2404.07008","repositories_listed":1,"syntology":null},{"url":"/paper/eraser-jailbreaking-defense-in-large-language","slug":"eraser-jailbreaking-defense-in-large-language","title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge","date":"2024-04-08","arxiv_id":"2404.05880","repositories_listed":1,"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/eraser-jailbreaking-defense-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2404.05880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05880"}},"official":{"repos":["ZeroNLP/Eraser"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/bear-a-unified-framework-for-evaluating","slug":"bear-a-unified-framework-for-evaluating","title":"BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language Models","date":"2024-04-05","arxiv_id":"2404.04113","repositories_listed":1,"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/bear-a-unified-framework-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2404.04113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04113"}},"official":{"repos":["lm-pub-quiz/lm-pub-quiz"],"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/benchmarking-large-language-models-for-2","slug":"benchmarking-large-language-models-for-2","title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","date":"2024-04-03","arxiv_id":"2404.02403","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-learning-via-meta-regularization","slug":"prompt-learning-via-meta-regularization","title":"Prompt Learning via Meta-Regularization","date":"2024-04-01","arxiv_id":"2404.00851","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/prompt-learning-via-meta-regularization#ran","syntology_url":"https://syntology.ai/paper/2404.00851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00851"}},"official":{"repos":["mlvlab/prometar"],"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/coin-a-benchmark-of-continual-instruction","slug":"coin-a-benchmark-of-continual-instruction","title":"CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model","date":"2024-03-13","arxiv_id":"2403.08350","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coin-a-benchmark-of-continual-instruction#ran","syntology_url":"https://syntology.ai/paper/2403.08350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08350"}},"official":{"repos":["zackschen/coin"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/see-through-their-minds-learning-transferable","slug":"see-through-their-minds-learning-transferable","title":"See Through Their Minds: Learning Transferable Neural Representation from Cross-Subject fMRI","date":"2024-03-11","arxiv_id":"2403.06361","repositories_listed":1,"syntology":null}],"syntology_records":37,"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":59,"papers_where_code_ran_first_page":"/task/general-knowledge/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":4,"url":"/task/general-knowledge/papers/2","json":"/task/general-knowledge/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/general-knowledge/papers/3","json":"/task/general-knowledge/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/general-knowledge/papers/4","json":"/task/general-knowledge/papers/4.json","rows":99},{"order":"ran","page":1,"of":1,"url":"/task/general-knowledge/papers/ran/1","json":"/task/general-knowledge/papers/ran/1.json","rows":59}],"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":"a2536e7f1d39d5722476f9b68e77948c84992a1fdd2823a8c3232e9380a9a818","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}