{"total":21,"rows":[{"id":"2210.03588","title":"Understanding Transformer Memorization Recall Through Idioms","created":"2022-10-07","cited_by_count":62,"area":null},{"id":"2401.07078","title":"PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities","created":"2024-01-13","cited_by_count":59,"area":null},{"id":"2403.05020","title":"Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs","created":"2024-03-08","cited_by_count":59,"area":null},{"id":"2212.10003","title":"(QA)$^2$: Question Answering with Questionable Assumptions","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2502.14301","title":"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models","created":"2025-02-20","cited_by_count":19,"area":null},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2311.09542","title":"Pregnant Questions: The Importance of Pragmatic Awareness in Maternal Health Question Answering","created":"2023-11-16","cited_by_count":14,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2502.13195","title":"Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs","created":"2025-02-18","cited_by_count":10,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2305.14785","title":"Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2306.16722","title":"Evaluating Paraphrastic Robustness in Textual Entailment Models","created":"2023-06-29","cited_by_count":7,"area":null},{"id":"2405.05776","title":"Experimental Pragmatics with Machines: Testing LLM Predictions for the Inferences of Plain and Embedded Disjunctions","created":"2024-05-09","cited_by_count":5,"area":null},{"id":"2306.11943","title":"Towards Understanding What Code Language Models Learned","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2506.06133","title":"Let's CONFER: A Dataset for Evaluating Natural Language Inference Models on CONditional InFERence and Presupposition","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2603.08358","title":"Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2607.18232","title":"It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2201.03521","title":"Polish Natural Language Inference and Factivity -- an Expert-based Dataset and Benchmarks","created":"2022-01-10","cited_by_count":0,"area":null},{"id":"2312.08755","title":"PROPRES: Investigating the Projectivity of Presupposition with Various Triggers and Environments","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2403.06301","title":"LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition","created":"2024-03-10","cited_by_count":0,"area":null},{"id":"2605.24267","title":"DRInQ: Evaluating Conversational Implicature with Controlled Context Variation","created":"2026-05-22","cited_by_count":0,"area":null}],"next_cursor":null}