{"total":126,"rows":[{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114,"area":null},{"id":"2311.09469","title":"Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs","created":"2023-11-16","cited_by_count":98,"area":null},{"id":"2410.13788","title":"Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions","created":"2024-10-17","cited_by_count":76,"area":null},{"id":"2507.22034","title":"UserBench: An Interactive Gym Environment for User-Centric Agents","created":"2025-07-29","cited_by_count":76,"area":"agents"},{"id":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73,"area":null},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57,"area":"alignment"},{"id":"2404.11972","title":"Aligning Language Models to Explicitly Handle Ambiguity","created":"2024-04-18","cited_by_count":56,"area":"agents"},{"id":"2305.13186","title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","created":"2023-05-22","cited_by_count":51,"area":"lr"},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50,"area":"agents"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2306.07075","title":"Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2410.23856","title":"Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?","created":"2024-10-31","cited_by_count":41,"area":"lr"},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2406.19073","title":"AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2311.09682","title":"MacGyver: Are Large Language Models Creative Problem Solvers?","created":"2023-11-16","cited_by_count":34,"area":null},{"id":"2402.11755","title":"SPML: A DSL for Defending Language Models Against Prompt Attacks","created":"2024-02-19","cited_by_count":34,"area":null},{"id":"2305.13788","title":"Can Large Language Models Capture Dissenting Human Voices?","created":"2023-05-23","cited_by_count":33,"area":null},{"id":"2311.09447","title":"How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities","created":"2023-11-15","cited_by_count":33,"area":null},{"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":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2306.10376","title":"CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents","created":"2023-06-17","cited_by_count":30,"area":"agents"},{"id":"2311.08398","title":"Are Large Language Models Temporally Grounded?","created":"2023-11-14","cited_by_count":27,"area":null},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2511.17959","title":"Towards Automating Data Access Permissions in AI Agents","created":"2025-11-22","cited_by_count":21,"area":null},{"id":"2507.23158","title":"User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal","created":"2025-07-30","cited_by_count":19,"area":null},{"id":"2406.14230","title":"Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2306.00824","title":"Zero and Few-shot Semantic Parsing with Ambiguous Inputs","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2310.13850","title":"Ecologically Valid Explanations for Label Variation in NLI","created":"2023-10-20","cited_by_count":16,"area":null},{"id":"2402.16102","title":"Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?","created":"2024-02-25","cited_by_count":15,"area":null},{"id":"2603.22868","title":"Agent-Sentry: Bounding LLM Agents via Execution Provenance","created":"2026-03-24","cited_by_count":15,"area":"agents"},{"id":"2504.01205","title":"Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2502.18448","title":"Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing","created":"2025-02-25","cited_by_count":13,"area":null},{"id":"2503.02233","title":"Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling","created":"2025-03-04","cited_by_count":13,"area":null},{"id":"2506.13342","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","created":"2025-06-16","cited_by_count":13,"area":null},{"id":"2310.13439","title":"Self-Consistency of Large Language Models under Ambiguity","created":"2023-10-20","cited_by_count":12,"area":"lr"},{"id":"2404.04332","title":"Scope Ambiguities in Large Language Models","created":"2024-04-05","cited_by_count":11,"area":null},{"id":"2405.16042","title":"Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention","created":"2024-05-25","cited_by_count":11,"area":null},{"id":"2409.19381","title":"HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoning","created":"2024-09-28","cited_by_count":11,"area":"lr"},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2402.17717","title":"AmbigNLG: Addressing Task Ambiguity in Instruction for NLG","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2404.00942","title":"Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs","created":"2024-04-01","cited_by_count":10,"area":null},{"id":"2506.06964","title":"Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2509.13905","title":"Do Large Language Models Understand Word Senses?","created":"2025-09-17","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":"2405.19010","title":"Evaluating the External and Parametric Knowledge Fusion of Large Language Models","created":"2024-05-29","cited_by_count":9,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2412.13835","title":"RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs","created":"2024-12-18","cited_by_count":8,"area":null},{"id":"2402.12486","title":"Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!","created":"2024-02-19","cited_by_count":7,"area":null},{"id":"2403.14072","title":"A Taxonomy of Ambiguity Types for NLP","created":"2024-03-21","cited_by_count":7,"area":null},{"id":"2410.18615","title":"FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation","created":"2024-10-24","cited_by_count":7,"area":null},{"id":"2505.10872","title":"REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?","created":"2025-05-16","cited_by_count":7,"area":"agents"},{"id":"2505.12543","title":"Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey","created":"2025-05-18","cited_by_count":6,"area":"agents"},{"id":"2401.07897","title":"The Pitfalls of Defining Hallucination","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2402.01423","title":"Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2405.20967","title":"Superlatives in Context: Modeling the Implicit Semantics of Superlatives","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2505.17222","title":"Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2510.16458","title":"Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations","created":"2025-10-18","cited_by_count":5,"area":null},{"id":"2403.05152","title":"Towards a Psychology of Machines: Large Language Models Predict Human Memory","created":"2024-03-08","cited_by_count":4,"area":null},{"id":"2403.09721","title":"A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2505.14549","title":"Can Large Language Models Really Recognize Your Name?","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2507.15114","title":"From Disagreement to Understanding: The Case for Ambiguity Detection in NLI","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2601.01754","title":"Context-Free Recognition with Transformers","created":"2026-01-05","cited_by_count":4,"area":null},{"id":"2602.16162","title":"LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2310.14610","title":"That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context?","created":"2023-10-23","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":"2408.12799","title":"Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora","created":"2024-08-23","cited_by_count":3,"area":"alignment"},{"id":"2506.01205","title":"Trick or Neat: Adversarial Ambiguity and Language Model Evaluation","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2509.12158","title":"Pun Unintended: LLMs and the Illusion of Humor Understanding","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2509.16107","title":"It Depends: Resolving Referential Ambiguity in Minimal Contexts with Commonsense Knowledge","created":"2025-09-19","cited_by_count":3,"area":null},{"id":"2510.14665","title":"Beyond \"Hallucinations\": A Framework for Stable Human-AI Reasoning","created":"2025-10-16","cited_by_count":3,"area":"lr"},{"id":"2605.25284","title":"Knowing but Not Showing: LLMs Recognize Ambiguity but Rarely Ask Clarifying Questions","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2308.10380","title":"A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2312.03726","title":"Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2508.19546","title":"Language Models Identify Ambiguities and Exploit Loopholes","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2512.09066","title":"ORCA: Open-ended Response Correctness Assessment for Audio Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2305.14750","title":"Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2402.13113","title":"When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2502.05793","title":"On Reference (In-)Determinacy in Natural Language Inference","created":"2025-02-09","cited_by_count":1,"area":null},{"id":"2504.02254","title":"LLMs as Deceptive Agents: How Role-Based Prompting Induces Semantic Ambiguity in Puzzle Tasks","created":"2025-04-03","cited_by_count":1,"area":"agents"},{"id":"2508.16697","title":"QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting","created":"2025-08-22","cited_by_count":1,"area":"lr"},{"id":"2509.14456","title":"Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2510.09390","title":"Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.17548","title":"When Annotators Disagree, Topology Explains: Mapper, a Topological Tool for Exploring Text Embedding Geometry and Ambiguity","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.13478","title":"NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.06666","title":"InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2601.11234","title":"How DDAIR you? Disambiguated Data Augmentation for Intent Recognition","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.11938","title":"Who is the richest club in the championship? Detecting and Rewriting Underspecified Questions Improve QA Performance","created":"2026-02-12","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":"2605.01168","title":"Quantifying and Predicting Disagreement in Graded Human Ratings","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2606.27669","title":"When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search","created":"2026-06-26","cited_by_count":1,"area":"agents"},{"id":"2608.08915","title":"Investigating Multimodal Informativity under Different Partner Visibility Conditions in Video-Mediated Dialogue","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2310.14657","title":"Reasoning about Ambiguous Definite Descriptions","created":"2023-10-23","cited_by_count":0,"area":"lr"},{"id":"2501.17569","title":"A linguistically-motivated evaluation methodology for unraveling model's abilities in reading comprehension tasks","created":"2025-01-29","cited_by_count":0,"area":null}],"next_cursor":"100"}