{"total":108,"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":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"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":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266,"area":"alignment"},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187,"area":"synth"},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"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":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170,"area":"lr"},{"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":"2311.07466","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","created":"2023-11-13","cited_by_count":73,"area":"lr"},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72,"area":"lr"},{"id":"2402.17262","title":"Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue","created":"2024-02-27","cited_by_count":66,"area":"safety"},{"id":"2310.18512","title":"Preventing Language Models From Hiding Their Reasoning","created":"2023-10-27","cited_by_count":65,"area":"lr"},{"id":"2408.17017","title":"Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling","created":"2024-08-30","cited_by_count":63,"area":"lr"},{"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":"2403.05518","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","created":"2024-03-08","cited_by_count":39,"area":"lr"},{"id":"2502.01142","title":"DeepRAG: Thinking to Retrieve Step by Step for Large Language Models","created":"2025-02-03","cited_by_count":38,"area":"lr"},{"id":"2309.06275","title":"Re-Reading Improves Reasoning in Large Language Models","created":"2023-09-12","cited_by_count":37,"area":"lr"},{"id":"2311.07961","title":"The ART of LLM Refinement: Ask, Refine, and Trust","created":"2023-11-14","cited_by_count":29,"area":null},{"id":"2402.11863","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","created":"2024-02-19","cited_by_count":29,"area":"lr"},{"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":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"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":"2506.22777","title":"Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning","created":"2025-06-28","cited_by_count":21,"area":"lr"},{"id":"2502.09673","title":"Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning","created":"2025-02-13","cited_by_count":20,"area":"lr"},{"id":"2402.04678","title":"FaithLM: Towards Faithful Explanations for Large Language Models","created":"2024-02-07","cited_by_count":19,"area":null},{"id":"2410.17635","title":"Markov Chain of Thought for Efficient Mathematical Reasoning","created":"2024-10-23","cited_by_count":19,"area":"lr"},{"id":"2407.02551","title":"Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses","created":"2024-07-02","cited_by_count":18,"area":"safety"},{"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":"2410.03864","title":"DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search","created":"2024-10-04","cited_by_count":17,"area":"lr"},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"id":"2309.13075","title":"SCREWS: A Modular Framework for Reasoning with Revisions","created":"2023-09-20","cited_by_count":16,"area":"lr"},{"id":"2410.07627","title":"Automatic Curriculum Expert Iteration for Reliable LLM Reasoning","created":"2024-10-10","cited_by_count":16,"area":"lr"},{"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":"2504.06438","title":"Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning","created":"2025-04-08","cited_by_count":15,"area":"lr"},{"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":"2502.11228","title":"Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs","created":"2025-02-16","cited_by_count":14,"area":"rag"},{"id":"2504.08893","title":"Knowledge Graph-extended Retrieval Augmented Generation for Question Answering","created":"2025-04-11","cited_by_count":14,"area":"rag"},{"id":"2505.17126","title":"Conformal Language Model Reasoning with Coherent Factuality","created":"2025-05-21","cited_by_count":14,"area":"lr"},{"id":"2402.14856","title":"Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning","created":"2024-02-20","cited_by_count":13,"area":"lr"},{"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":"2505.23945","title":"A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models","created":"2025-05-29","cited_by_count":12,"area":"lr"},{"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":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"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":"2405.00711","title":"Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities","created":"2024-04-25","cited_by_count":8,"area":"diffusion"},{"id":"2406.16144","title":"Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step","created":"2024-06-23","cited_by_count":8,"area":"lr"},{"id":"2506.12509","title":"Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs","created":"2025-06-14","cited_by_count":8,"area":"lr"},{"id":"2603.22582","title":"Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2603.28590","title":"MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models","created":"2026-03-30","cited_by_count":8,"area":"lr"},{"id":"2409.19339","title":"Visual Question Decomposition on Multimodal Large Language Models","created":"2024-09-28","cited_by_count":7,"area":"mllm"},{"id":"2402.12806","title":"SymBa: Symbolic Backward Chaining for Structured Natural Language Reasoning","created":"2024-02-20","cited_by_count":6,"area":"lr"},{"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":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2311.08263","title":"Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster","created":"2023-11-14","cited_by_count":5,"area":"lr"},{"id":"2404.13985","title":"Information Re-Organization Improves Reasoning in Large Language Models","created":"2024-04-22","cited_by_count":5,"area":"lr"},{"id":"2506.08927","title":"Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"id":"2510.24236","title":"Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?","created":"2025-10-28","cited_by_count":5,"area":"lr"},{"id":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"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":"2412.04537","title":"Understanding Hidden Computations in Chain-of-Thought Reasoning","created":"2024-12-05","cited_by_count":4,"area":"lr"},{"id":"2509.16369","title":"Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction","created":"2025-09-19","cited_by_count":4,"area":"agents"},{"id":"2603.20172","title":"Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation","created":"2026-03-20","cited_by_count":4,"area":"lr"},{"id":"2604.07012","title":"DTCRS: Dynamic Tree Construction for Recursive Summarization","created":"2026-04-08","cited_by_count":4,"area":"rag"},{"id":"2604.10693","title":"FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning","created":"2026-04-12","cited_by_count":4,"area":"lr"},{"id":"2402.01602","title":"Foundation Model Sherpas: Guiding Foundation Models through Knowledge and Reasoning","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2602.02619","title":"daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently","created":"2026-02-02","cited_by_count":3,"area":"agents"},{"id":"2309.12767","title":"Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models","created":"2023-09-22","cited_by_count":2,"area":"lr"},{"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":"2512.10422","title":"Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers","created":"2025-12-11","cited_by_count":2,"area":"rag"},{"id":"2602.21728","title":"Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling","created":"2026-02-25","cited_by_count":2,"area":"lr"},{"id":"2605.11746","title":"When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"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":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2506.11246","title":"No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning","created":"2025-06-12","cited_by_count":1,"area":"lr"},{"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":"2605.14358","title":"Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2607.20833","title":"REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"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":"2506.22893","title":"Agentic Enterprise: AI-Centric User to User-Centric AI","created":"2025-06-28","cited_by_count":0,"area":"agents"},{"id":"2601.02991","title":"Towards Faithful Reasoning in Comics for Small MLLMs","created":"2026-01-06","cited_by_count":0,"area":"lr"},{"id":"2604.15726","title":"LLM Reasoning Is Latent, Not the Chain of Thought","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.04070","title":"Toward Human-AI Complementarity Across Diverse Tasks","created":"2026-04-13","cited_by_count":0,"area":null}],"next_cursor":"100"}