Faithfulness of Language Model Reasoning

Follow this topic Ask about this topic

Latest papers

41 papers20 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Chain of Faith: Policy-Internal Rewards for Reasoning Reliance
Nov 2, 2026Fanyu meng, Zhaodan Kong, Xin LiuFaithfulness of Language Model Reasoning RL for Language Model Reasoning
University of California, Davis
Chain-of-Thought Oversight Requires Separate Evidence for Faithfulness and Monitorability
Nov 1, 2026Sichao Li, Sai Ma, Xiyang Hu +2CoT Monitoring Faithfulness of Language Model Reasoning
The University of Sydney · MINT Lab, Johns Hopkins University · Australian National University +2
Evidence-grounded large language models guide perovskite solar cell design and optimization
Oct 31, 2026YanKai Chen, Zhi Wan, ZiHao Li +1Large Language Model-Guided Scientific Discovery Scientific Reasoning in Language Models
School of Materials Science and Engineering, Tsinghua University, Beijing 100084, P. R. China. · College of Bioresources Chemical and Materials Engineering, Shaanxi University of Science & Technology, Xi’an 710021, P. R. China. · Department of Chemical Engineering, Tsinghua University, Beijing 100084, P. R. China.
CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness
Oct 30, 2026Xiao Yu, Justin Chih-Yao Chen, Zaid Khan +2RL for Language Model Reasoning CoT Faithfulness
UNC Chapel Hill
Beyond Selected Breakthroughs: Evaluating Language Models on Randomly Sampled Mathematical Conjectures
Oct 29, 2026Helen Jenne, Davis Brown, Jesse He +1LLM Mathematical Reasoning AI-Assisted Mathematical Discovery
Pacific Northwest National Laboratory · University of Pennsylvania · University of California San Diego +1
Does Chain-of-Thought Reliance Follow a Scaling Law?Larger Models Follow Their Steps More, Independent of Post-Training
Oct 28, 2026Esther XinFaithfulness of Language Model Reasoning Language Model Reasoning Evaluation
Independent Researcher
Natural Language Autoencoders Identify Without Explaining
Oct 23, 2026Kristina Šekrst, Barbara GeldLLM Interpretability Faithfulness of Language Model Explanations
LLMs Can Tackle High Energy Theoretical Physics, yet Gaps Remain: Part I, Quantum Field Theory
Oct 23, 2026Tong Liu, Bohan Li, Gongrui Cheng +3Scientific Reasoning in Language Models Language Model Reasoning Evaluation
Ludwig-Maximilians-Universität München, München, Germany · Munich Center for Machine Learning · Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan +3
Many Perturbations, Shared Failure Dynamics: Tracing Direction-Sensitive Perturbation Influence in Language Models
Oct 23, 2026Zhibo Hu, Chen Wang, Yanfeng Shu +3Language Model Robustness Faithfulness of Language Model Reasoning
The University of New South Wales Australia · CSIRO technology Australia
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
Oct 22, 2026Gabriele Dominici, Teague McMillan, Fazl Barez +2Structured Reasoning in Language Models Faithfulness of Language Model Reasoning
Università della Svizzera Italiana · ETH Zurich · University of Oxford
Would an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR Examination
Oct 22, 2026Miguel Fernandez-de-Retana, Unai Zulaika, Ruben Sanchez-Corcuera +2Clinical Language Model Evaluation Medical QA
Faculty of Engineering, University of Deusto (Bilbao, Spain)
Tracing Hallucinations in LLM Reasoning for UML Class Diagram Generation: An Empirical Taxonomy and Mitigation Study
Oct 22, 2026Mojdeh Rahmanian, Foutse Khomh, Ashkan Sami +1Hallucination in Language Models LLM Hallucination Mitigation
Edinburgh Napier University, Edinburgh, Scotland · Polytechnique Montréal, Montréal, QC, Canada
Interpreting Model Reasoning through Behavioral Counterfactuals
Oct 22, 2026Shawn Im, James Oldfield, Adel Bibi +1Causal Interventions in Language Models Faithfulness of Language Model Reasoning
University of Wisconsin–Madison · University of Oxford
Monitorability Is Trainable: Post-Training for Chain-of-Thought Monitorability
Oct 21, 2026Usman Anwar, Tim Bakker, Christos Louizos +1CoT Monitoring LLM Post-Training
University of Cambridge · Qualcomm AI Research · Mila, University of Montreal
Mitigating Query Shortcuts in Chain-of-Thought with Context-Aware Decoding
Oct 21, 2026Shin'ya YamaguchiCoT Reasoning Faithfulness of Language Model Reasoning
NTT
Computation, Not Memory: Chain-of-Thought and State Tracking in LLM Agents
Oct 19, 2026Pedram Mouseli, Massieh MoayediCoT Reasoning Multi-Turn Language Model Reasoning
University of Toronto
CoTs remain monitorable when being unfaithful requires computation: Replicating and Extending the Necessity Effect Across Eleven Models
Oct 17, 2026Arav Dhoot, Yixiong Hao, Zephaniah RoeFaithfulness of Language Model Reasoning Faithfulness of Language Model Explanations
Columbia University · Second Look Research
Verbalising Model's Computation for Chain-of-Thought Faithfulness Detection
Oct 16, 2026Yujing Wang, Yulan He, Wenya Wang +1CoT Faithfulness Faithfulness of Language Model Reasoning
King’s College London · Nanyang Technological University
What LLMs Do in the Shadows: Reading Context Reliance from the Unembedding Dark Space
Oct 16, 2026Alexandra Kuleshova, Andrey Volodichev, Daria Kotova +1LLM Hallucination Detection Faithfulness of Language Model Reasoning
Applied AI Institute
The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls
Oct 16, 2026Lucas Resck, Jingyi Sun, Qianli Wang +2CoT Faithfulness Faithfulness of Language Model Reasoning
Language Technology Lab, University of Cambridge · University of Copenhagen · Technische Universität Berlin +1
Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning
Oct 5, 2026Boyue Caroline Hu, Kaivalya Ahir, Ronghao Ni +1LLM Auditing Software Vulnerability Detection
Carnegie Mellon University, Pittsburgh, Pennsilvanya, USA
Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability
Oct 2, 2026Samuel Lewis-Lim, Xingwei Tan, Mario Sanger +2Faithfulness of Language Model Reasoning Efficient Language Model Reasoning
School of Computer Science, University of Sheffield · AstraZeneca
From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
Sep 19, 2026Qianli Wang, Yilong Wang, Dennis Wei +5CoT Faithfulness LLM Interpretability
Technische Universität Berlin · German Research Center for Artificial Intelligence (DFKI) · IBM Research +4
Reason-Mediated Behavioral Models for Auditing LLM Social Simulators
Jul 27, 2026Atharva Pandey, Gautam JajooLLM Auditing Human Behavior Simulation
Kairosity
Not All LLM Reasoning is Visible in the Chain-of-Thought
Jul 24, 2026Vatsal Baherwani, Tom Goldstein, Ashwinee PandaCoT Faithfulness LLM Interpretability
New York University · University of Maryland · TogetherAI
Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning
Jun 15, 2026Olivia Peiyu Wang, Sanna Wong-Toropainen, Daneshvar Amrollahi +4Faithfulness of Language Model Reasoning LLM Reliability
UC Santa Cruz · Univ. Helsinki · CodeX, Stanford +4
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
May 29, 2026Yan Wang, Zhixuan Chu, Zihao Xue +9LLM Guardrails Faithfulness of Language Model Reasoning
Alibaba Group · Zhejiang University · Huzhou Normal University +1
Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
May 26, 2026Pruthvinath Jeripity VenkataLLM Uncertainty Estimation Faithfulness of Language Model Explanations
Independent Researcher
Learning Faithful Reasoning Processes with Spatio-Temporal Latent Dynamics for Large Language Models
May 26, 2026Weijiang Lv, Wentong Zhao, Jiayu Wang +3CoT Faithfulness RL for Language Model Reasoning
Xidian University · Xi’an Jiaotong University · Mohamed bin Zayed University of Artificial Intelligence +2
Retrieval-Augmented Linguistic Calibration
May 19, 2026Yi-Fan Yeh, Linwei Tao, Minjing Dong +4Confidence Estimation in Language Models Faithfulness of Language Model Reasoning
School of Computer Science University of Sydney Sydney, Australia · City University of Hong Kong Hong Kong · Shanghai Jiao Tong University Shanghai, China +1

Nov 2, 2026J/K move · Enter open · S save

Chain of Faith: Policy-Internal Rewards for Reasoning Reliance

Fanyu meng, Zhaodan Kong, Xin Liu

University of California, Davis

Faithfulness of Language Model Reasoning RL for Language Model Reasoning Language Model Reasoning Evaluation

Open paper AskPDF arXiv

Chain-of-thought (CoT) explanations can sound plausible while having little influence on a model's final answer. We study four rewards that use the policy's own signals to encourage reliance on generated reasoning: gradient sensitivity, confidence gaps, progressive confidence gains, and reasoning--prompt swaps. We add each reward to group relative policy optimization (GRPO) and evaluate two small instruction-tuned models on GSM8K and StrategyQA using reasoning edits, paraphrases, and prompt hints. Several configurations increase answer reliance to reasoning edits, while effects on accuracy and paraphrase robustness vary. We also observe answer copying at a high reward weight and high reliance in decomposition settings with poor task accuracy. The study compares practical objectives for reasoning reliance, confirms the trade-off between reliance and performance, and proposes four lightweight rewards that can improve reasoning reliance.