{"total":70,"rows":[{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122,"area":"lr"},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940,"area":"lr"},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703,"area":"lr"},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288,"area":"lr"},{"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":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110,"area":"lr"},{"id":"2307.11768","title":"Question Decomposition Improves the Faithfulness of Model-Generated Reasoning","created":"2023-07-17","cited_by_count":108,"area":"lr"},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87,"area":"lr"},{"id":"2306.06427","title":"Boosting Language Models Reasoning with Chain-of-Knowledge Prompting","created":"2023-06-10","cited_by_count":77,"area":"lr"},{"id":"2310.00280","title":"Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration","created":"2023-09-30","cited_by_count":70,"area":"lr"},{"id":"2402.06044","title":"OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models","created":"2024-02-08","cited_by_count":54,"area":"lr"},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53,"area":"lr"},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2204.05514","title":"A Comparative Study of Faithfulness Metrics for Model Interpretability Methods","created":"2022-04-12","cited_by_count":39,"area":"lr"},{"id":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29,"area":"lr"},{"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":"2510.04040","title":"FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning","created":"2025-10-05","cited_by_count":26,"area":"lr"},{"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":"2510.23482","title":"On the Faithfulness of Visual Thinking: Measurement and Enhancement","created":"2025-10-27","cited_by_count":17,"area":"lr"},{"id":"2305.10496","title":"Incorporating Attribution Importance for Improving Faithfulness Metrics","created":"2023-05-17","cited_by_count":14,"area":"lr"},{"id":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2206.11212","title":"VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives","created":"2022-06-22","cited_by_count":12,"area":"lr"},{"id":"2602.17053","title":"RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2204.07693","title":"Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes","created":"2022-04-16","cited_by_count":9,"area":"lr"},{"id":"2308.15118","title":"Large Language Models on the Chessboard: A Study on ChatGPT's Formal Language Comprehension and Complex Reasoning Skills","created":"2023-08-29","cited_by_count":9,"area":"lr"},{"id":"2409.07123","title":"Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem","created":"2024-09-11","cited_by_count":9,"area":"lr"},{"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":"2602.11201","title":"Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning","created":"2026-02-04","cited_by_count":9,"area":"lr"},{"id":"2605.12671","title":"All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs","created":"2026-05-12","cited_by_count":9,"area":"lr"},{"id":"2410.11900","title":"FLARE: Faithful Logic-Aided Reasoning and Exploration","created":"2024-10-14","cited_by_count":7,"area":"lr"},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2508.16213","title":"MedOmni-45{\\deg}: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2601.07663","title":"Reasoning Models Will Sometimes Lie About Their Reasoning","created":"2026-01-12","cited_by_count":6,"area":"lr"},{"id":"2603.16475","title":"Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2503.11248","title":"Reasoning-Grounded Natural Language Explanations for Language Models","created":"2025-03-14","cited_by_count":5,"area":"lr"},{"id":"2603.30036","title":"Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?","created":"2026-03-31","cited_by_count":5,"area":"lr"},{"id":"2311.06985","title":"Large Language Models are In-context Teachers for Knowledge Reasoning","created":"2023-11-12","cited_by_count":4,"area":"lr"},{"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":"2409.15359","title":"Watch Your Steps: Observable and Modular Chains of Thought","created":"2024-09-17","cited_by_count":3,"area":"lr"},{"id":"2510.00319","title":"DecepChain: Inducing Deceptive Reasoning in Large Language Models","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2607.20935","title":"Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad","created":"2026-07-23","cited_by_count":3,"area":"lr"},{"id":"2505.24217","title":"Semi-structured LLM Reasoners Can Be Rigorously Audited","created":"2025-05-30","cited_by_count":2,"area":"lr"},{"id":"2602.09832","title":"LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse","created":"2026-02-10","cited_by_count":2,"area":"lr"},{"id":"2607.12815","title":"Visual Access Boundaries in Vision-Language Model Reasoning","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2603.22816","title":"Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness","created":"2026-03-24","cited_by_count":1,"area":"lr"},{"id":"2606.05625","title":"Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2606.12706","title":"VLADriveBench: Evaluating CoT-Action Relationship in VLA for Autonomous Driving","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2606.13156","title":"Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2608.22332","title":"Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching","created":"2026-08-23","cited_by_count":1,"area":"lr"},{"id":"2505.23323","title":"Neither Stochastic Parroting nor AGI: LLMs Solve Tasks through Context-Directed Extrapolation from Training Data Priors","created":"2025-05-29","cited_by_count":0,"area":"lr"},{"id":"2508.08273","title":"TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning","created":"2025-07-30","cited_by_count":0,"area":"lr"},{"id":"2510.01236","title":"GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2510.08613","title":"GraphGhost: Tracing Structures Behind Large Language Models","created":"2025-10-07","cited_by_count":0,"area":"lr"},{"id":"2512.22258","title":"Logic Sketch Prompting (LSP): A Deterministic and Interpretable Prompting Method","created":"2025-12-24","cited_by_count":0,"area":"lr"},{"id":"2602.06446","title":"CORE: Comprehensive Ontological Relation Evaluation for Large Language Models","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2602.14002","title":"The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2604.09890","title":"Should We be Pedantic About Reasoning Errors in Machine Translation?","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2604.14641","title":"Learning to Draw ASCII Improves Spatial Reasoning in Language Models","created":"2026-04-16","cited_by_count":0,"area":"lr"},{"id":"2604.16158","title":"AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2604.22156","title":"Sum-of-Checks: Structured Reasoning for Surgical Safety with Large Vision-Language Models","created":"2026-04-24","cited_by_count":0,"area":"lr"},{"id":"2606.15779","title":"Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2607.04572","title":"Context-Masked Truncated Reasoning Audits for Answer-Key Dependence in LLM Tutors","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2609.36984","title":"REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.01076","title":"GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR Events","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.01938","title":"A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.03509","title":"Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.15107","title":"Structural Chain-of-Thought: Reasoning with Executable Computational Graphs","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}