{"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/informativeness","name":"Informativeness","slug":"informativeness","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":735,"papers_with_code":266,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/crisismmd","name":"CrisisMMD","full_name":"","num_papers_in_archive":25}],"subtasks":[],"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":8,"rows_per_page":100,"shown":100,"of":735,"of_with_code":266,"tagged_in_all":735,"counts":{"archive_papers_tagged":735,"with_a_code_link":266,"where_syntology_ran_a_sample":58,"not_listed_spam_title":0,"listed":735,"listed_where_code_ran":58,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":44,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":44,"listed_every_run_a_failure_of_syntologys_instrument":14,"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-to-navigate-for-fine-grained","slug":"learning-to-navigate-for-fine-grained","title":"Learning to Navigate for Fine-grained Classification","date":"2018-09-02","arxiv_id":"1809.00287","repositories_listed":12,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"9 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-navigate-for-fine-grained#ran","syntology_url":"https://syntology.ai/paper/1809.00287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.00287"}},"official":{"repos":["yangze0930/NTS-Net"],"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/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/nrpa-neural-recommendation-with-personalized","slug":"nrpa-neural-recommendation-with-personalized","title":"NRPA: Neural Recommendation with Personalized Attention","date":"2019-05-29","arxiv_id":"1905.12480","repositories_listed":5,"syntology":null},{"url":"/paper/generating-informative-and-diverse","slug":"generating-informative-and-diverse","title":"Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization","date":"2018-09-16","arxiv_id":"1809.05972","repositories_listed":4,"syntology":null},{"url":"/paper/unsupervised-abstractive-meeting","slug":"unsupervised-abstractive-meeting","title":"Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization","date":"2018-05-14","arxiv_id":"1805.05271","repositories_listed":4,"syntology":null},{"url":"/paper/dataset-distillation-via-factorization","slug":"dataset-distillation-via-factorization","title":"Dataset Distillation via Factorization","date":"2022-10-30","arxiv_id":"2210.16774","repositories_listed":3,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/dataset-distillation-via-factorization#ran","syntology_url":"https://syntology.ai/paper/2210.16774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16774"}},"official":{"repos":["huage001/datasetfactorization"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bartscore-evaluating-generated-text-as-text","slug":"bartscore-evaluating-generated-text-as-text","title":"BARTScore: Evaluating Generated Text as Text Generation","date":"2021-06-22","arxiv_id":"2106.11520","repositories_listed":3,"syntology":null},{"url":"/paper/response-generation-by-context-aware","slug":"response-generation-by-context-aware","title":"Response Generation by Context-aware Prototype Editing","date":"2018-06-19","arxiv_id":"1806.07042","repositories_listed":3,"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/response-generation-by-context-aware#ran","syntology_url":"https://syntology.ai/paper/1806.07042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.07042"}},"official":{"repos":["MarkWuNLP/ResponseEdit"],"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/icym2i-the-illusion-of-multimodal","slug":"icym2i-the-illusion-of-multimodal","title":"ICYM2I: The illusion of multimodal informativeness under missingness","date":"2025-05-22","arxiv_id":"2505.16953","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/icym2i-the-illusion-of-multimodal#ran","syntology_url":"https://syntology.ai/paper/2505.16953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16953"}},"official":{"repos":["reAIM-Lab/ICYM2I","reAIM-Lab/ehr_foundation_model_benchmark"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/whisperner-unified-open-named-entity-and","slug":"whisperner-unified-open-named-entity-and","title":"WhisperNER: Unified Open Named Entity and Speech Recognition","date":"2024-09-12","arxiv_id":"2409.08107","repositories_listed":2,"syntology":null},{"url":"/paper/deepedit-knowledge-editing-as-decoding-with","slug":"deepedit-knowledge-editing-as-decoding-with","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","date":"2024-01-19","arxiv_id":"2401.10471","repositories_listed":2,"syntology":null},{"url":"/paper/infoverse-a-universal-framework-for-dataset","slug":"infoverse-a-universal-framework-for-dataset","title":"infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information","date":"2023-05-30","arxiv_id":"2305.19344","repositories_listed":2,"syntology":null},{"url":"/paper/summarizing-stream-data-for-memory-restricted","slug":"summarizing-stream-data-for-memory-restricted","title":"Summarizing Stream Data for Memory-Constrained Online Continual Learning","date":"2023-05-26","arxiv_id":"2305.16645","repositories_listed":2,"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/summarizing-stream-data-for-memory-restricted#ran","syntology_url":"https://syntology.ai/paper/2305.16645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16645"}},"official":{"repos":["vimar-gu/ssd"],"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/gaussian-switch-sampling-a-second-order","slug":"gaussian-switch-sampling-a-second-order","title":"Gaussian Switch Sampling: A Second Order Approach to Active Learning","date":"2023-02-16","arxiv_id":"2302.12018","repositories_listed":2,"syntology":null},{"url":"/paper/task-oriented-communication-for-edge-video","slug":"task-oriented-communication-for-edge-video","title":"Task-Oriented Communication for Edge Video Analytics","date":"2022-11-25","arxiv_id":"2211.14049","repositories_listed":2,"syntology":null},{"url":"/paper/progen-progressive-zero-shot-dataset","slug":"progen-progressive-zero-shot-dataset","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","date":"2022-10-22","arxiv_id":"2210.12329","repositories_listed":2,"syntology":null},{"url":"/paper/meta-query-net-resolving-purity","slug":"meta-query-net-resolving-purity","title":"Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning","date":"2022-10-13","arxiv_id":"2210.07805","repositories_listed":2,"syntology":{"n":13,"n_ran":7,"n_constructed":2,"n_ran_checked":5,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/meta-query-net-resolving-purity#ran","syntology_url":"https://syntology.ai/paper/2210.07805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07805"}},"official":{"repos":["kaist-dmlab/mqnet"],"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/metaug-contrastive-learning-via-meta-feature","slug":"metaug-contrastive-learning-via-meta-feature","title":"MetAug: Contrastive Learning via Meta Feature Augmentation","date":"2022-03-10","arxiv_id":"2203.05119","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"4 ran (of which 2 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) · 0 unverified","sample_list":"/paper/metaug-contrastive-learning-via-meta-feature#ran","syntology_url":"https://syntology.ai/paper/2203.05119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05119"}},"official":{"repos":["jiangmengli/metaug","lionellee9089/metaug"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/graph-prototypical-networks-for-few-shot","slug":"graph-prototypical-networks-for-few-shot","title":"Graph Prototypical Networks for Few-shot Learning on Attributed Networks","date":"2020-06-23","arxiv_id":"2006.12739","repositories_listed":2,"syntology":null},{"url":"/paper/foreshadowing-the-benefits-of-incidental","slug":"foreshadowing-the-benefits-of-incidental","title":"Foreseeing the Benefits of Incidental Supervision","date":"2020-06-09","arxiv_id":"2006.05500","repositories_listed":2,"syntology":null},{"url":"/paper/joint-keyphrase-chunking-and-salience-ranking","slug":"joint-keyphrase-chunking-and-salience-ranking","title":"Capturing Global Informativeness in Open Domain Keyphrase Extraction","date":"2020-04-28","arxiv_id":"2004.13639","repositories_listed":2,"syntology":null},{"url":"/paper/theory-and-evaluation-metrics-for-learning","slug":"theory-and-evaluation-metrics-for-learning","title":"Theory and Evaluation Metrics for Learning Disentangled Representations","date":"2019-08-26","arxiv_id":"1908.09961","repositories_listed":2,"syntology":null},{"url":"/paper/pragmatically-informative-text-generation","slug":"pragmatically-informative-text-generation","title":"Pragmatically Informative Text Generation","date":"2019-04-02","arxiv_id":"1904.01301","repositories_listed":2,"syntology":null},{"url":"/paper/exploiting-unlabeled-data-in-cnns-by-self","slug":"exploiting-unlabeled-data-in-cnns-by-self","title":"Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank","date":"2019-02-17","arxiv_id":"1902.06285","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/exploiting-unlabeled-data-in-cnns-by-self#ran","syntology_url":"https://syntology.ai/paper/1902.06285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.06285"}},"official":null}},{"url":"/paper/domain-agnostic-real-valued-specificity","slug":"domain-agnostic-real-valued-specificity","title":"Domain Agnostic Real-Valued Specificity Prediction","date":"2018-11-13","arxiv_id":"1811.05085","repositories_listed":2,"syntology":null},{"url":"/paper/prosody-modifications-for-question-answering","slug":"prosody-modifications-for-question-answering","title":"Prosody Modifications for Question-Answering in Voice-Only Settings","date":"2018-06-11","arxiv_id":"1806.03957","repositories_listed":2,"syntology":null},{"url":"/paper/neural-extractive-summarization-with-side","slug":"neural-extractive-summarization-with-side","title":"Neural Extractive Summarization with Side Information","date":"2017-04-14","arxiv_id":"1704.04530","repositories_listed":2,"syntology":null},{"url":"/paper/semantically-conditioned-lstm-based-natural","slug":"semantically-conditioned-lstm-based-natural","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","date":"2015-08-07","arxiv_id":"1508.01745","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/semantically-conditioned-lstm-based-natural#ran","syntology_url":"https://syntology.ai/paper/1508.01745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.01745"}},"official":null}},{"url":"/paper/multi-preference-lambda-weighted-listwise-dpo","slug":"multi-preference-lambda-weighted-listwise-dpo","title":"Multi-Preference Lambda-weighted Listwise DPO for Dynamic Preference Alignment","date":"2025-06-24","arxiv_id":"2506.19780","repositories_listed":1,"syntology":null},{"url":"/paper/cure-cultural-gaps-in-the-long-tail-of-text","slug":"cure-cultural-gaps-in-the-long-tail-of-text","title":"CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems","date":"2025-06-09","arxiv_id":"2506.08071","repositories_listed":1,"syntology":null},{"url":"/paper/eru-kg-efficient-reference-aligned","slug":"eru-kg-efficient-reference-aligned","title":"ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation","date":"2025-05-30","arxiv_id":"2505.24219","repositories_listed":1,"syntology":null},{"url":"/paper/power-law-decay-loss-for-large-language-model","slug":"power-law-decay-loss-for-large-language-model","title":"Power-Law Decay Loss for Large Language Model Finetuning: Focusing on Information Sparsity to Enhance Generation Quality","date":"2025-05-22","arxiv_id":"2505.16900","repositories_listed":1,"syntology":null},{"url":"/paper/laplace-sample-information-data","slug":"laplace-sample-information-data","title":"Laplace Sample Information: Data Informativeness Through a Bayesian Lens","date":"2025-05-21","arxiv_id":"2505.15303","repositories_listed":1,"syntology":null},{"url":"/paper/judging-the-judges-can-large-vision-language","slug":"judging-the-judges-can-large-vision-language","title":"Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?","date":"2025-05-13","arxiv_id":"2505.08468","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-unified-representation-evaluation","slug":"towards-a-unified-representation-evaluation","title":"Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks","date":"2025-05-09","arxiv_id":"2505.06224","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-evaluating-long-form","slug":"an-empirical-study-of-evaluating-long-form","title":"An Empirical Study of Evaluating Long-form Question Answering","date":"2025-04-25","arxiv_id":"2504.18413","repositories_listed":1,"syntology":null},{"url":"/paper/machine-learning-interpretation-of-optical","slug":"machine-learning-interpretation-of-optical","title":"Machine Learning Interpretation of Optical Spectroscopy Using Peak-Sensitive Logistic Regression","date":"2025-04-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/respec-relevance-and-specificity-grounded","slug":"respec-relevance-and-specificity-grounded","title":"ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams","date":"2025-04-21","arxiv_id":"2504.14875","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/respec-relevance-and-specificity-grounded#ran","syntology_url":"https://syntology.ai/paper/2504.14875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14875"}},"official":{"repos":["cdjkim/respec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/transfer-learning-for-temporal-link","slug":"transfer-learning-for-temporal-link","title":"Transfer Learning for Temporal Link Prediction","date":"2025-04-15","arxiv_id":"2504.10925","repositories_listed":1,"syntology":null},{"url":"/paper/wikiautogen-towards-multi-modal-wikipedia","slug":"wikiautogen-towards-multi-modal-wikipedia","title":"WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation","date":"2025-03-24","arxiv_id":"2503.19065","repositories_listed":1,"syntology":null},{"url":"/paper/considering-length-diversity-in-retrieval","slug":"considering-length-diversity-in-retrieval","title":"Considering Length Diversity in Retrieval-Augmented Summarization","date":"2025-03-12","arxiv_id":"2503.09249","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-information-gaps-with-comprehensive","slug":"bridging-information-gaps-with-comprehensive","title":"Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions","date":"2025-02-24","arxiv_id":"2502.17715","repositories_listed":1,"syntology":null},{"url":"/paper/multi-view-contrastive-network-mcnet-for","slug":"multi-view-contrastive-network-mcnet-for","title":"MVCNet: Multi-View Contrastive Network for Motor Imagery Classification","date":"2025-02-18","arxiv_id":"2502.17482","repositories_listed":1,"syntology":null},{"url":"/paper/reversum-a-multi-staged-retrieval-augmented","slug":"reversum-a-multi-staged-retrieval-augmented","title":"REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives","date":"2025-02-17","arxiv_id":"2502.12137","repositories_listed":1,"syntology":null},{"url":"/paper/truth-knows-no-language-evaluating","slug":"truth-knows-no-language-evaluating","title":"Truth Knows No Language: Evaluating Truthfulness Beyond English","date":"2025-02-13","arxiv_id":"2502.09387","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/truth-knows-no-language-evaluating#ran","syntology_url":"https://syntology.ai/paper/2502.09387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.09387"}},"official":{"repos":["hitz-zentroa/truthfulqa-multi"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/learning-conformal-abstention-policies-for","slug":"learning-conformal-abstention-policies-for","title":"Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models","date":"2025-02-08","arxiv_id":"2502.06884","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"8 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; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/learning-conformal-abstention-policies-for#ran","syntology_url":"https://syntology.ai/paper/2502.06884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06884"}},"official":{"repos":["sinatayebati/vlm-uncertainty"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-llm-via-learning-from-data","slug":"boosting-llm-via-learning-from-data","title":"Boosting LLM via Learning from Data Iteratively and Selectively","date":"2024-12-23","arxiv_id":"2412.17365","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-contextual-informativeness-in-child","slug":"measuring-contextual-informativeness-in-child","title":"Measuring Contextual Informativeness in Child-Directed Text","date":"2024-12-23","arxiv_id":"2412.17427","repositories_listed":1,"syntology":null},{"url":"/paper/face-the-facts-evaluating-rag-based-fact","slug":"face-the-facts-evaluating-rag-based-fact","title":"Face the Facts! Evaluating RAG-based Fact-checking Pipelines in Realistic Settings","date":"2024-12-19","arxiv_id":"2412.15189","repositories_listed":1,"syntology":null},{"url":"/paper/pa-rag-rag-alignment-via-multi-perspective","slug":"pa-rag-rag-alignment-via-multi-perspective","title":"PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization","date":"2024-12-19","arxiv_id":"2412.14510","repositories_listed":1,"syntology":null},{"url":"/paper/what-has-been-overlooked-in-contrastive","slug":"what-has-been-overlooked-in-contrastive","title":"What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context","date":"2024-12-18","arxiv_id":"2412.14301","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 1 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) · 0 unverified","sample_list":"/paper/what-has-been-overlooked-in-contrastive#ran","syntology_url":"https://syntology.ai/paper/2412.14301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14301"}},"official":{"repos":["jingwang18/silan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/vg-tvp-multimodal-procedural-planning-via","slug":"vg-tvp-multimodal-procedural-planning-via","title":"VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting","date":"2024-12-16","arxiv_id":"2412.11621","repositories_listed":1,"syntology":null},{"url":"/paper/dg-mamba-robust-and-efficient-dynamic-graph","slug":"dg-mamba-robust-and-efficient-dynamic-graph","title":"DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models","date":"2024-12-11","arxiv_id":"2412.08160","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 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; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dg-mamba-robust-and-efficient-dynamic-graph#ran","syntology_url":"https://syntology.ai/paper/2412.08160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08160"}},"official":{"repos":["RingBDStack/DG-Mamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/class-balance-matters-to-active-class","slug":"class-balance-matters-to-active-class","title":"Class Balance Matters to Active Class-Incremental Learning","date":"2024-12-09","arxiv_id":"2412.06642","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-bayesian-active-learning-with","slug":"multi-label-bayesian-active-learning-with","title":"Multi-Label Bayesian Active Learning with Inter-Label Relationships","date":"2024-11-26","arxiv_id":"2411.17941","repositories_listed":1,"syntology":null},{"url":"/paper/dtels-towards-dynamic-granularity-of-timeline","slug":"dtels-towards-dynamic-granularity-of-timeline","title":"DTELS: Towards Dynamic Granularity of Timeline Summarization","date":"2024-11-14","arxiv_id":"2411.09297","repositories_listed":1,"syntology":null},{"url":"/paper/multi-expert-prompting-improves-reliability","slug":"multi-expert-prompting-improves-reliability","title":"Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models","date":"2024-11-01","arxiv_id":"2411.00492","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-expert-prompting-improves-reliability#ran","syntology_url":"https://syntology.ai/paper/2411.00492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00492"}},"official":{"repos":["dxlong2000/multi-expert-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-embodied-reinforcement-learning","slug":"teaching-embodied-reinforcement-learning","title":"Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use","date":"2024-10-31","arxiv_id":"2410.24218","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/teaching-embodied-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2410.24218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24218"}},"official":{"repos":["sled-group/teachable_rl"],"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/contrastive-learning-and-adversarial","slug":"contrastive-learning-and-adversarial","title":"Contrastive Learning and Adversarial Disentanglement for Task-Oriented Semantic Communications","date":"2024-10-30","arxiv_id":"2410.22784","repositories_listed":1,"syntology":null},{"url":"/paper/graph-based-uncertainty-metrics-for-long-form","slug":"graph-based-uncertainty-metrics-for-long-form","title":"Graph-based Uncertainty Metrics for Long-form Language Model Outputs","date":"2024-10-28","arxiv_id":"2410.20783","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/graph-based-uncertainty-metrics-for-long-form#ran","syntology_url":"https://syntology.ai/paper/2410.20783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20783"}},"official":{"repos":["mingjianjiang-1/graph-based-uncertainty"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/medlogic-aqa-enhancing-medical-question","slug":"medlogic-aqa-enhancing-medical-question","title":"MedLogic-AQA: Enhancing Medical Question Answering with Abstractive Models Focusing on Logical Structures","date":"2024-10-20","arxiv_id":"2410.15463","repositories_listed":1,"syntology":null},{"url":"/paper/miceval-unveiling-multimodal-chain-of-thought","slug":"miceval-unveiling-multimodal-chain-of-thought","title":"MiCEval: Unveiling Multimodal Chain of Thought's Quality via Image Description and Reasoning Steps","date":"2024-10-18","arxiv_id":"2410.14668","repositories_listed":1,"syntology":null},{"url":"/paper/tell-me-what-i-need-to-know-exploring-llm","slug":"tell-me-what-i-need-to-know-exploring-llm","title":"Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization","date":"2024-10-18","arxiv_id":"2410.14545","repositories_listed":1,"syntology":null},{"url":"/paper/generative-subgraph-retrieval-for-knowledge","slug":"generative-subgraph-retrieval-for-knowledge","title":"Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation","date":"2024-10-12","arxiv_id":"2410.09350","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generative-subgraph-retrieval-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2410.09350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09350"}},"official":{"repos":["mlvlab/dialoggsr"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-fragility-of-fairness-causal-sensitivity","slug":"the-fragility-of-fairness-causal-sensitivity","title":"The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning","date":"2024-10-12","arxiv_id":"2410.09600","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/the-fragility-of-fairness-causal-sensitivity#ran","syntology_url":"https://syntology.ai/paper/2410.09600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09600"}},"official":{"repos":["jakefawkes/fragile_fair"],"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/faithcamera-construction-of-a-faithful","slug":"faithcamera-construction-of-a-faithful","title":"FaithCAMERA: Construction of a Faithful Dataset for Ad Text Generation","date":"2024-10-04","arxiv_id":"2410.03839","repositories_listed":1,"syntology":null},{"url":"/paper/generating-bilingual-example-sentences-with","slug":"generating-bilingual-example-sentences-with","title":"Generating bilingual example sentences with large language models as lexicography assistants","date":"2024-10-04","arxiv_id":"2410.03182","repositories_listed":1,"syntology":null},{"url":"/paper/hiddenguard-fine-grained-safe-generation-with","slug":"hiddenguard-fine-grained-safe-generation-with","title":"HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router","date":"2024-10-03","arxiv_id":"2410.02684","repositories_listed":1,"syntology":null},{"url":"/paper/best-practices-for-multi-fidelity-bayesian","slug":"best-practices-for-multi-fidelity-bayesian","title":"Best Practices for Multi-Fidelity Bayesian Optimization in Materials and Molecular Research","date":"2024-10-01","arxiv_id":"2410.00544","repositories_listed":1,"syntology":null},{"url":"/paper/distribution-discrepancy-and-feature","slug":"distribution-discrepancy-and-feature","title":"Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection","date":"2024-09-09","arxiv_id":"2409.05425","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-open-set-active-learning-with","slug":"adaptive-open-set-active-learning-with","title":"Adaptive Open-Set Active Learning with Distance-Based Out-of-Distribution Detection for Robust Task-Oriented Dialog System","date":"2024-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/glimmer-incorporating-graph-and-lexical","slug":"glimmer-incorporating-graph-and-lexical","title":"GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization","date":"2024-08-19","arxiv_id":"2408.10115","repositories_listed":1,"syntology":null},{"url":"/paper/robust-offline-active-learning-on-graphs","slug":"robust-offline-active-learning-on-graphs","title":"Robust Offline Active Learning on Graphs","date":"2024-08-15","arxiv_id":"2408.07941","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-and-modeling-correlations-in","slug":"bridging-and-modeling-correlations-in","title":"Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization","date":"2024-08-14","arxiv_id":"2408.07471","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/bridging-and-modeling-correlations-in#ran","syntology_url":"https://syntology.ai/paper/2408.07471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07471"}},"official":{"repos":["YJiangcm/BMC"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/avoid-wasted-annotation-costs-in-open-set","slug":"avoid-wasted-annotation-costs-in-open-set","title":"Avoid Wasted Annotation Costs in Open-set Active Learning with Pre-trained Vision-Language Model","date":"2024-08-09","arxiv_id":"2408.04917","repositories_listed":1,"syntology":null},{"url":"/paper/conversational-dueling-bandits-in-generalized","slug":"conversational-dueling-bandits-in-generalized","title":"Conversational Dueling Bandits in Generalized Linear Models","date":"2024-07-26","arxiv_id":"2407.18488","repositories_listed":1,"syntology":null},{"url":"/paper/token-level-correlation-guided-compression","slug":"token-level-correlation-guided-compression","title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding","date":"2024-07-19","arxiv_id":"2407.14439","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-prototypes-enhancing-transparency","slug":"semantic-prototypes-enhancing-transparency","title":"Semantic Prototypes: Enhancing Transparency Without Black Boxes","date":"2024-07-18","arxiv_id":"2407.15871","repositories_listed":1,"syntology":null},{"url":"/paper/what-s-wrong-refining-meeting-summaries-with","slug":"what-s-wrong-refining-meeting-summaries-with","title":"What's Wrong? Refining Meeting Summaries with LLM Feedback","date":"2024-07-16","arxiv_id":"2407.11919","repositories_listed":1,"syntology":null},{"url":"/paper/b-dpo-direct-preference-optimization-with","slug":"b-dpo-direct-preference-optimization-with","title":"$β$-DPO: Direct Preference Optimization with Dynamic $β$","date":"2024-07-11","arxiv_id":"2407.08639","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/b-dpo-direct-preference-optimization-with#ran","syntology_url":"https://syntology.ai/paper/2407.08639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08639"}},"official":{"repos":["junkangwu/beta-dpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enriching-information-and-preserving-semantic","slug":"enriching-information-and-preserving-semantic","title":"Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets","date":"2024-07-11","arxiv_id":"2407.08209","repositories_listed":1,"syntology":null},{"url":"/paper/core-robust-factual-precision-scoring-with","slug":"core-robust-factual-precision-scoring-with","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","date":"2024-07-04","arxiv_id":"2407.03572","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-constant-negative-rewards-for-goal","slug":"revisiting-constant-negative-rewards-for-goal","title":"Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning","date":"2024-06-29","arxiv_id":"2407.00324","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-ask-informative-questions","slug":"learning-to-ask-informative-questions","title":"Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain","date":"2024-06-25","arxiv_id":"2406.17453","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"0 ran · 5 unverified","sample_list":"/paper/learning-to-ask-informative-questions#ran","syntology_url":"https://syntology.ai/paper/2406.17453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17453"}},"official":{"repos":["dmazzaccara/learningtoask"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/trustworthy-enhanced-multi-view-multi-modal","slug":"trustworthy-enhanced-multi-view-multi-modal","title":"Trustworthy Enhanced Multi-view Multi-modal Alzheimer's Disease Prediction with Brain-wide Imaging Transcriptomics Data","date":"2024-06-21","arxiv_id":"2406.14977","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-by-design-audio-segmentation","slug":"explainable-by-design-audio-segmentation","title":"Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing","date":"2024-06-19","arxiv_id":"2406.13385","repositories_listed":1,"syntology":null},{"url":"/paper/crisissense-llm-instruction-fine-tuned-large","slug":"crisissense-llm-instruction-fine-tuned-large","title":"CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics","date":"2024-06-16","arxiv_id":"2406.15477","repositories_listed":1,"syntology":null},{"url":"/paper/improving-paratope-and-epitope-prediction-by","slug":"improving-paratope-and-epitope-prediction-by","title":"Improving Paratope and Epitope Prediction by Multi-Modal Contrastive Learning and Interaction Informativeness Estimation","date":"2024-05-31","arxiv_id":"2405.20668","repositories_listed":1,"syntology":null},{"url":"/paper/kg-fit-knowledge-graph-fine-tuning-upon-open","slug":"kg-fit-knowledge-graph-fine-tuning-upon-open","title":"KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge","date":"2024-05-26","arxiv_id":"2405.16412","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/kg-fit-knowledge-graph-fine-tuning-upon-open#ran","syntology_url":"https://syntology.ai/paper/2405.16412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16412"}},"official":{"repos":["pat-jj/KG-FIT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automated-evaluation-of-retrieval-augmented","slug":"automated-evaluation-of-retrieval-augmented","title":"Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation","date":"2024-05-22","arxiv_id":"2405.13622","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-emergence-in-large-language","slug":"quantifying-emergence-in-large-language","title":"Quantifying Semantic Emergence in Language Models","date":"2024-05-21","arxiv_id":"2405.12617","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/quantifying-emergence-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2405.12617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12617"}},"official":{"repos":["zodiark-ch/emergence-of-llms"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/conformal-alignment-knowing-when-to-trust","slug":"conformal-alignment-knowing-when-to-trust","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","date":"2024-05-16","arxiv_id":"2405.10301","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conformal-alignment-knowing-when-to-trust#ran","syntology_url":"https://syntology.ai/paper/2405.10301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10301"}},"official":{"repos":["yugjerry/conformal-alignment"],"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/informativeness-of-weighted-conformal","slug":"informativeness-of-weighted-conformal","title":"Informativeness of Weighted Conformal Prediction","date":"2024-05-10","arxiv_id":"2405.06479","repositories_listed":1,"syntology":null},{"url":"/paper/predictive-accuracy-based-active-learning-for","slug":"predictive-accuracy-based-active-learning-for","title":"Predictive Accuracy-Based Active Learning for Medical Image Segmentation","date":"2024-05-01","arxiv_id":"2405.00452","repositories_listed":1,"syntology":null},{"url":"/paper/markovian-agents-for-truthful-language","slug":"markovian-agents-for-truthful-language","title":"Markovian Transformers for Informative Language Modeling","date":"2024-04-29","arxiv_id":"2404.18988","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":5,"n_pointer_only":16,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/markovian-agents-for-truthful-language#ran","syntology_url":"https://syntology.ai/paper/2404.18988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18988"}},"official":{"repos":["scottviteri/markoviantraining"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-in-latent-representations-of","slug":"uncertainty-in-latent-representations-of","title":"Uncertainty in latent representations of variational autoencoders optimized for visual tasks","date":"2024-04-23","arxiv_id":"2404.15390","repositories_listed":1,"syntology":null},{"url":"/paper/valor-eval-holistic-coverage-and-faithfulness","slug":"valor-eval-holistic-coverage-and-faithfulness","title":"VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models","date":"2024-04-22","arxiv_id":"2404.13874","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/valor-eval-holistic-coverage-and-faithfulness#ran","syntology_url":"https://syntology.ai/paper/2404.13874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13874"}},"official":{"repos":["haoyiq114/valor"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/self-supervised-dataset-distillation-a-good","slug":"self-supervised-dataset-distillation-a-good","title":"Self-supervised Dataset Distillation: A Good Compression Is All You Need","date":"2024-04-11","arxiv_id":"2404.07976","repositories_listed":1,"syntology":null},{"url":"/paper/take-a-look-at-it-rethinking-how-to-evaluate","slug":"take-a-look-at-it-rethinking-how-to-evaluate","title":"Rethinking How to Evaluate Language Model Jailbreak","date":"2024-04-09","arxiv_id":"2404.06407","repositories_listed":1,"syntology":null}],"syntology_records":28,"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":58,"papers_where_code_ran_first_page":"/task/informativeness/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":8,"url":"/task/informativeness/papers/2","json":"/task/informativeness/papers/2.json","rows":100},{"order":"archive","page":3,"of":8,"url":"/task/informativeness/papers/3","json":"/task/informativeness/papers/3.json","rows":100},{"order":"archive","page":4,"of":8,"url":"/task/informativeness/papers/4","json":"/task/informativeness/papers/4.json","rows":100},{"order":"archive","page":5,"of":8,"url":"/task/informativeness/papers/5","json":"/task/informativeness/papers/5.json","rows":100},{"order":"archive","page":6,"of":8,"url":"/task/informativeness/papers/6","json":"/task/informativeness/papers/6.json","rows":100},{"order":"archive","page":7,"of":8,"url":"/task/informativeness/papers/7","json":"/task/informativeness/papers/7.json","rows":100},{"order":"archive","page":8,"of":8,"url":"/task/informativeness/papers/8","json":"/task/informativeness/papers/8.json","rows":35},{"order":"ran","page":1,"of":1,"url":"/task/informativeness/papers/ran/1","json":"/task/informativeness/papers/ran/1.json","rows":58}],"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":"48fbc0e3b21a811511a7e941328e69f55c341f9e4870274aef25843abcb83be0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}