{"total":42,"rows":[{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040,"area":null},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324,"area":null},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177,"area":null},{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"area":null},{"id":"2311.09677","title":"R-Tuning: Instructing Large Language Models to Say `I Don't Know'","created":"2023-11-16","cited_by_count":111,"area":null},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2409.01658","title":"From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning","created":"2024-09-03","cited_by_count":54,"area":null},{"id":"2311.07961","title":"The ART of LLM Refinement: Ask, Refine, and Trust","created":"2023-11-14","cited_by_count":29,"area":null},{"id":"2404.03189","title":"The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models","created":"2024-04-04","cited_by_count":29,"area":null},{"id":"2402.02392","title":"DeLLMa: Decision Making Under Uncertainty with Large Language Models","created":"2024-02-04","cited_by_count":21,"area":null},{"id":"2403.10779","title":"LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention via Everyday Smart Devices","created":"2024-03-16","cited_by_count":21,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2402.04678","title":"FaithLM: Towards Faithful Explanations for Large Language Models","created":"2024-02-07","cited_by_count":19,"area":null},{"id":"2409.10790","title":"Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering","created":"2024-09-16","cited_by_count":17,"area":null},{"id":"2410.11302","title":"Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs","created":"2024-10-15","cited_by_count":15,"area":null},{"id":"2407.18008","title":"GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy","created":"2024-07-25","cited_by_count":14,"area":null},{"id":"2402.14833","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","created":"2024-02-17","cited_by_count":12,"area":null},{"id":"2310.00259","title":"AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models","created":"2023-09-30","cited_by_count":10,"area":null},{"id":"2406.03827","title":"Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2310.02174","title":"Ask Again, Then Fail: Large Language Models' Vacillations in Judgment","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2402.17097","title":"Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses","created":"2024-02-27","cited_by_count":6,"area":null},{"id":"2410.19301","title":"Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2311.09613","title":"Digital Socrates: Evaluating LLMs through Explanation Critiques","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2407.18712","title":"Cluster-norm for Unsupervised Probing of Knowledge","created":"2024-07-26","cited_by_count":4,"area":null},{"id":"2311.09558","title":"What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perception","created":"2023-11-16","cited_by_count":2,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2507.02306","title":"Synthetic Heuristic Evaluation: A Comparison between AI- and Human-Powered Usability Evaluation","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2310.11266","title":"Emulating Human Cognitive Processes for Expert-Level Medical Question-Answering with Large Language Models","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2311.05754","title":"Deep Natural Language Feature Learning for Interpretable Prediction","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2401.15724","title":"RE-GAINS & EnChAnT: Intelligent Tool Manipulation Systems For Enhanced Query Responses","created":"2024-01-28","cited_by_count":1,"area":null},{"id":"2412.15101","title":"Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2508.01763","title":"Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2603.01274","title":"GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Models","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2310.07093","title":"Argumentative Stance Prediction: An Exploratory Study on Multimodality and Few-Shot Learning","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2505.08402","title":"TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlers","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2605.04070","title":"Toward Human-AI Complementarity Across Diverse Tasks","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2607.21090","title":"Training Large Language Models for Self-Explanation Faithfulness","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.04343","title":"A Removal Based Approach to Improve LLM Faithfulness at Test-Time","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.32825","title":"The Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.01514","title":"How the Audit Rule Shapes Faithful Factor Explanations in LLMs","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}