{"url":"/task/negation","name":"Negation","slug":"negation","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":608,"papers_with_code":173,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/ovdeval","name":"OVDEval","full_name":"","num_papers_in_archive":4},{"url":"/dataset/thunder-nubench","name":"Thunder-NUBench","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":173,"tagged_in_all":608,"items":[{"url":"/paper/editing-models-with-task-arithmetic","title":"Editing Models with Task Arithmetic","date":"2022-12-08","arxiv_id":"2212.04089","repositories_listed":9,"syntology":{"n":15,"n_ran":5,"n_unverified":10,"n_pointer_only":4}},{"url":"/paper/beta-embeddings-for-multi-hop-logical","title":"Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs","date":"2020-10-22","arxiv_id":"2010.11465","repositories_listed":9,"syntology":{"n":14,"n_ran":8,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","arxiv_id":"2104.06378","repositories_listed":6,"syntology":{"n":25,"n_ran":1,"n_unverified":24,"n_pointer_only":4}},{"url":"/paper/logic-embeddings-for-complex-query-answering","title":"Logic Embeddings for Complex Query Answering","date":"2021-02-28","arxiv_id":"2103.00418","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/ratescore-a-metric-for-radiology-report","title":"RaTEScore: A Metric for Radiology Report Generation","date":"2024-06-24","arxiv_id":"2406.16845","repositories_listed":3,"syntology":null},{"url":"/paper/analogs-of-linguistic-structure-in-deep","title":"Analogs of Linguistic Structure in Deep Representations","date":"2017-07-25","arxiv_id":"1707.08139","repositories_listed":3,"syntology":null},{"url":"/paper/fast-and-accurate-sentiment-classification","title":"Fast and accurate sentiment classification using an enhanced Naive Bayes model","date":"2013-05-27","arxiv_id":"1305.6143","repositories_listed":3,"syntology":null},{"url":"/paper/reproducing-nevir-negation-in-neural","title":"Reproducing NevIR: Negation in Neural Information Retrieval","date":"2025-02-19","arxiv_id":"2502.13506","repositories_listed":2,"syntology":null},{"url":"/paper/ask-again-then-fail-large-language-models","title":"Ask Again, Then Fail: Large Language Models' Vacillations in Judgment","date":"2023-10-03","arxiv_id":"2310.02174","repositories_listed":2,"syntology":null},{"url":"/paper/resolving-legalese-a-multilingual-exploration","title":"Resolving Legalese: A Multilingual Exploration of Negation Scope Resolution in Legal Documents","date":"2023-09-15","arxiv_id":"2309.08695","repositories_listed":2,"syntology":null},{"url":"/paper/this-is-not-correct-negation-aware-evaluation","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","date":"2023-07-26","arxiv_id":"2307.13989","repositories_listed":2,"syntology":null},{"url":"/paper/composing-parameter-efficient-modules-with","title":"Composing Parameter-Efficient Modules with Arithmetic Operations","date":"2023-06-26","arxiv_id":"2306.14870","repositories_listed":2,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":4}},{"url":"/paper/multi-task-learning-of-negation-and","title":"Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification","date":"2020-10-16","arxiv_id":"2010.08318","repositories_listed":2,"syntology":null},{"url":"/paper/sentibert-a-transferable-transformer-based","title":"SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics","date":"2020-05-08","arxiv_id":"2005.04114","repositories_listed":2,"syntology":null},{"url":"/paper/negated-lama-birds-cannot-fly","title":"Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly","date":"2019-11-08","arxiv_id":"1911.03343","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/explanation-by-progressive-exaggeration-1","title":"Explanation by Progressive Exaggeration","date":"2019-11-01","arxiv_id":"1911.00483","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/what-bert-is-not-lessons-from-a-new-suite-of","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","date":"2019-07-31","arxiv_id":"1907.13528","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/evaluating-scoped-meaning-representations","title":"Evaluating Scoped Meaning Representations","date":"2018-02-23","arxiv_id":"1802.08599","repositories_listed":2,"syntology":null},{"url":"/paper/mazebase-a-sandbox-for-learning-from-games","title":"MazeBase: A Sandbox for Learning from Games","date":"2015-11-23","arxiv_id":"1511.07401","repositories_listed":2,"syntology":null},{"url":"/paper/probing-the-geometry-of-truth-consistency-and","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","date":"2025-06-01","arxiv_id":"2506.00823","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/2505-11314","title":"CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks","date":"2025-05-16","arxiv_id":"2505.11314","repositories_listed":1,"syntology":null},{"url":"/paper/formalmath-benchmarking-formal-mathematical","title":"FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models","date":"2025-05-05","arxiv_id":"2505.02735","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/negativas-a-prototype-for-searching-and","title":"negativas: a prototype for searching and classifying sentential negation in speech data","date":"2025-04-05","arxiv_id":"2504.04275","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-model-editing-with-task-localized","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","date":"2025-04-03","arxiv_id":"2504.02620","repositories_listed":1,"syntology":null},{"url":"/paper/is-clip-ideal-no-can-we-fix-it-yes","title":"Is CLIP ideal? No. Can we fix it? Yes!","date":"2025-03-10","arxiv_id":"2503.08723","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-model-editing-with-task-vector","title":"Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach","date":"2025-02-03","arxiv_id":"2502.01015","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/solving-zero-shot-3d-visual-grounding-as","title":"Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems","date":"2024-11-21","arxiv_id":"2411.14594","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-language-and-diffusion-models-by","title":"Controlling Language and Diffusion Models by Transporting Activations","date":"2024-10-30","arxiv_id":"2410.23054","repositories_listed":1,"syntology":null},{"url":"/paper/automatically-generating-visual-hallucination","title":"Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models","date":"2024-10-15","arxiv_id":"2410.11242","repositories_listed":1,"syntology":null},{"url":"/paper/negmerge-consensual-weight-negation-for","title":"NegMerge: Consensual Weight Negation for Strong Machine Unlearning","date":"2024-10-08","arxiv_id":"2410.05583","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}}],"syntology_records":12,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}