{"total":73,"rows":[{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126,"area":null},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"area":null},{"id":"2211.17257","title":"CREPE: Open-Domain Question Answering with False Presuppositions","created":"2022-11-30","cited_by_count":72,"area":null},{"id":"2212.06801","title":"A fine-grained comparison of pragmatic language understanding in humans and language models","created":"2022-12-13","cited_by_count":70,"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":"2212.10003","title":"(QA)$^2$: Question Answering with Questionable Assumptions","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2101.00391","title":"Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering","created":"2021-01-02","cited_by_count":41,"area":null},{"id":"2106.06830","title":"Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP","created":"2021-06-12","cited_by_count":31,"area":null},{"id":"2502.12378","title":"Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges","created":"2025-02-17","cited_by_count":31,"area":null},{"id":"2101.04640","title":"Dimensions of Commonsense Knowledge","created":"2021-01-12","cited_by_count":29,"area":null},{"id":"2104.10343","title":"Sensitivity as a Complexity Measure for Sequence Classification Tasks","created":"2021-04-21","cited_by_count":28,"area":null},{"id":"2106.01195","title":"Figurative Language in Recognizing Textual Entailment","created":"2021-06-02","cited_by_count":26,"area":null},{"id":"2109.06987","title":"NOPE: A Corpus of Naturally-Occurring Presuppositions in English","created":"2021-09-14","cited_by_count":23,"area":null},{"id":"2502.21098","title":"Re-evaluating Theory of Mind evaluation in large language models","created":"2025-02-28","cited_by_count":23,"area":null},{"id":"2212.08979","title":"Language model acceptability judgements are not always robust to context","created":"2022-12-18","cited_by_count":22,"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":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17,"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":"2401.14440","title":"Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models","created":"2024-01-25","cited_by_count":14,"area":null},{"id":"2305.07666","title":"Imitation versus Innovation: What children can do that large language and language-and-vision models cannot (yet)?","created":"2023-05-08","cited_by_count":13,"area":null},{"id":"2107.00807","title":"He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics","created":"2021-07-02","cited_by_count":12,"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":"2405.05135","title":"Lessons from the Use of Natural Language Inference (NLI) in Requirements Engineering Tasks","created":"2024-04-24","cited_by_count":12,"area":null},{"id":"2502.08080","title":"NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals","created":"2025-02-12","cited_by_count":11,"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":"2506.08952","title":"Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2304.04758","title":"Expectations over Unspoken Alternatives Predict Pragmatic Inferences","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2501.07719","title":"Entailed Between the Lines: Incorporating Implication into NLI","created":"2025-01-13","cited_by_count":9,"area":null},{"id":"2502.06204","title":"Non-literal Understanding of Number Words by Language Models","created":"2025-02-10","cited_by_count":9,"area":null},{"id":"2107.07229","title":"Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task","created":"2021-07-15","cited_by_count":8,"area":null},{"id":"2206.14729","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks","created":"2022-06-29","cited_by_count":8,"area":null},{"id":"2305.18657","title":"Representation Of Lexical Stylistic Features In Language Models' Embedding Space","created":"2023-05-29","cited_by_count":8,"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":"2305.16259","title":"Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization","created":"2023-05-25","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":"2106.01207","title":"Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning","created":"2021-06-02","cited_by_count":5,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"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":"2406.17282","title":"SetBERT: Enhancing Retrieval Performance for Boolean Logic and Set Operation Queries","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2408.06673","title":"Pragmatic inference of scalar implicature by LLMs","created":"2024-08-13","cited_by_count":5,"area":null},{"id":"2307.02269","title":"SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2104.07623","title":"Sometimes We Want Translationese","created":"2021-04-15","cited_by_count":3,"area":null},{"id":"2112.02333","title":"LoNLI: An Extensible Framework for Testing Diverse Logical Reasoning Capabilities for NLI","created":"2021-12-04","cited_by_count":3,"area":null},{"id":"2404.03301","title":"Probing Large Language Models for Scalar Adjective Lexical Semantics and Scalar Diversity Pragmatics","created":"2024-04-04","cited_by_count":3,"area":null},{"id":"2411.05172","title":"ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentence","created":"2024-11-07","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":"2506.06775","title":"They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2403.04314","title":"Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2510.26253","title":"Pragmatic Theories Enhance Understanding of Implied Meanings in LLMs","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2107.03884","title":"CANDLE: Decomposing Conditional and Conjunctive Queries for Task-Oriented Dialogue Systems","created":"2021-07-08","cited_by_count":1,"area":null},{"id":"2408.11189","title":"Emotional RAG LLMs: Reading Comprehension for the Open Internet","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2502.14119","title":"Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora Accessibility","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2505.09005","title":"For GPT-4 as with Humans: Information Structure Predicts Acceptability of Long-Distance Dependencies","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2602.23546","title":"Humans and LLMs Diverge on Probabilistic Inferences","created":"2026-02-26","cited_by_count":1,"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":"2210.08097","title":"TestAug: A Framework for Augmenting Capability-based NLP Tests","created":"2022-10-14","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":"2405.09293","title":"Do language models capture implied discourse meanings? An investigation with exhaustivity implicatures of Korean morphology","created":"2024-05-15","cited_by_count":0,"area":null},{"id":"2503.01269","title":"ChatGPT for President! Presupposed content in politicians versus GPT-generated texts","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2506.00065","title":"Using Perspectival Words Is Harder Than Vocabulary Words for Humans and Even More So for Multimodal Language Models","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2510.21575","title":"From Polyester Girlfriends to Blind Mice: Creating the First Pragmatics Understanding Benchmarks for Slovene","created":"2025-10-24","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},{"id":"2607.25094","title":"Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.03340","title":"Benchmarking the Benchmarks: Testing the Predictive Validity of Commonsense Benchmarks","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.01788","title":"VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.37497","title":"Larry Caused the Car to Stop, But the Model Didn't Notice: Transformer Blindness to the M-Heuristic","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.14438","title":"Neither True nor False: Do LLMs Represent Truth-Value Gaps in Plural Predication?","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}