{"total":19,"rows":[{"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":"2603.05167","title":"C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning","created":"2026-03-05","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":"2601.07663","title":"Reasoning Models Will Sometimes Lie About Their Reasoning","created":"2026-01-12","cited_by_count":6,"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":"2603.26410","title":"Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models","created":"2026-03-27","cited_by_count":4,"area":"lr"},{"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":"2605.24286","title":"Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning","created":"2026-05-22","cited_by_count":3,"area":"lr"},{"id":"2605.25603","title":"Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy","created":"2026-05-25","cited_by_count":3,"area":"lr"},{"id":"2602.07833","title":"SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models","created":"2026-02-08","cited_by_count":2,"area":"lr"},{"id":"2605.01704","title":"The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning","created":"2026-05-03","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":"2607.23458","title":"Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are Wrong","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2604.16913","title":"The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus","created":"2026-04-18","cited_by_count":0,"area":"lr"},{"id":"2605.26795","title":"What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2605.26893","title":"GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought","created":"2026-05-26","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":"2608.13221","title":"TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.37788","title":"A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}