{"total":58,"rows":[{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"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":"2310.17567","title":"Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models","created":"2023-10-26","cited_by_count":64,"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":"2408.05636","title":"Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion","created":"2024-08-10","cited_by_count":57,"area":"inference"},{"id":"2309.08591","title":"Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings","created":"2023-09-15","cited_by_count":32,"area":"lr"},{"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":"2402.09193","title":"(Ir)rationality and Cognitive Biases in Large Language Models","created":"2024-02-14","cited_by_count":23,"area":"lr"},{"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":"2303.13988","title":"Machine Psychology","created":"2023-03-24","cited_by_count":22,"area":null},{"id":"2305.07716","title":"Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning","created":"2023-05-12","cited_by_count":16,"area":"lr"},{"id":"2305.01020","title":"Evaluating statistical language models as pragmatic reasoners","created":"2023-05-01","cited_by_count":15,"area":"lr"},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2305.17311","title":"Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2409.14195","title":"The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends","created":"2024-09-21","cited_by_count":11,"area":null},{"id":"2508.12461","title":"Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models","created":"2025-08-17","cited_by_count":11,"area":"moe"},{"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":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","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":"2503.01513","title":"Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2503.01539","title":"Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language","created":"2025-03-03","cited_by_count":8,"area":"lr"},{"id":"2408.01460","title":"LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models","created":"2024-07-27","cited_by_count":7,"area":null},{"id":"2411.01562","title":"Are LLMs good pragmatic speakers?","created":"2024-11-03","cited_by_count":7,"area":null},{"id":"2502.15821","title":"Towards Robust ESG Analysis Against Greenwashing Risks: Aspect-Action Analysis with Cross-Category Generalization","created":"2025-02-20","cited_by_count":7,"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":"2505.18497","title":"The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models","created":"2025-05-24","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":"2509.24102","title":"From Training to Generalization: Improving Moral Reasoning Through Pragmatic Inference","created":"2025-09-28","cited_by_count":2,"area":"lr"},{"id":"2510.26253","title":"Pragmatic Theories Enhance Understanding of Implied Meanings in LLMs","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2607.03598","title":"They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2402.09494","title":"Can AI and humans genuinely communicate?","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2405.08760","title":"Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs","created":"2024-05-14","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":"2410.06235","title":"Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learning","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2506.01474","title":"Integrating Neural and Symbolic Components in a Model of Pragmatic Question-Answering","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2606.01845","title":"Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2403.05701","title":"Are Large Language Models Aligned with People's Social Intuitions for Human-Robot Interactions?","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2408.03074","title":"Towards an Analysis of Discourse and Interactional Pragmatic Reasoning Capabilities of Large Language Models","created":"2024-08-06","cited_by_count":0,"area":"lr"},{"id":"2410.14395","title":"Generative AI, Pragmatics, and Authenticity in Second Language Learning","created":"2024-10-18","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":"2510.25426","title":"Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2603.09993","title":"CEI: A Benchmark for Evaluating Pragmatic Reasoning in Language Models","created":"2026-02-14","cited_by_count":0,"area":"lr"},{"id":"2603.19997","title":"When Contextual Inference Fails: Cancelability in Interactive Instruction Following","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.20479","title":"Profiling learners' affective engagement: Emotion AI, intercultural pragmatics, and language learning","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.07006","title":"Continuous Interpretive Steering for Scalar Diversity","created":"2026-04-08","cited_by_count":0,"area":"mechinterp"},{"id":"2604.17718","title":"Do LLMs Use Cultural Knowledge Without Being Told? A Multilingual Evaluation of Implicit Pragmatic Adaptation","created":"2026-04-20","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":"2606.17688","title":"LLMs Infer Cultural Context but Fail to Apply It When Responding","created":"2026-06-16","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":"2608.09551","title":"Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.28560","title":"A Formal Limitation on Learning Human Language From Textual Corpora","created":"2026-08-28","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":"2609.28487","title":"Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022-2025","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.29001","title":"Polite but Misaligned: Evaluating LLM Politeness Judgments Against Human Pragmatic Norms","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.13794","title":"Not Just an Evaluation: A Case Study of Discourse Particle Sensitivity in Language Models","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}