Faithfulness of Language Model Explanations

Ask about this topic

Overview

This topic asks whether a model’s explanations identify the evidence and reasoning that actually influence its answers, rather than merely offering plausible justifications afterward. Researchers test this with counterfactual prompt and evidence edits, feature ablations, activation probes and patching, and citation or verifier checks across reasoning, medical, classification, and retrieval-augmented tasks. To improve faithfulness, methods include evidence-grounded generation, structured or executable reasoning, and training with faithfulness rewards. A central challenge is that correct answers and convincing explanations do not prove causal faithfulness, while metrics often disagree and improvements can trade off against accuracy, completeness, or brevity.

Latest papers

CardsList

107 papers25 papers in the last four weeks, up 39% on the four weeks before. 0.1% of all new papers.

  1. Same Verdict, Different Readers: Personalizing Fact-Checking Explanations from Relative Preferences

    Oct 27, 2026Haokun Wen, Xuemeng Song, Mong-Li Lee +1Automated Fact-CheckingPersonalized Language Model Alignment

    National University of Singapore Singapore · Southern University of Science and Technology Shenzhen, China

  2. Faithful Explanations under Missing Modalities in Multimodal Dementia Prognosis

    Oct 26, 2026Firuz KamalovFaithfulness of Language Model ExplanationsMultimodal Model Interpretability

    Canadian University Dubai, City Walk, P.O. Box 117781, Dubai, United Arab Emirates

  3. Natural Language Autoencoders Identify Without Explaining

    Oct 23, 2026Kristina Šekrst, Barbara GeldLLM InterpretabilityFaithfulness of Language Model Explanations

  4. Do Language Models Trust Their Own Justifications? A Study on Functional Consistency

    Oct 23, 2026Alisson Rosa Pereira, Bruno Iochins GrisciFaithfulness of Language Model ExplanationsLLM Evaluation

    Institute of Informatics Universidade Federal do Rio Grande do Sul Porto Alegre, Brazil

  5. Judging the Justification: Decision Certificate Supervision for Generative Reward Models

    Oct 20, 2026Guiquan Sun, Bing Bai, Martin Renqiang Min +1Reward ModelingFaithfulness of Language Model Explanations

    School of Computing, University of Connecticut · NEC Labs America

  6. TxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event Sequences

    Oct 19, 2026Rabimba Karanjai, Yiming Bian, Yun-Shiuan Chuang +9Financial Language Model EvaluationFinancial Reasoning in Language Models

    PayPal AI · University of Pennsylvania

  7. Beyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulation

    Oct 19, 2026Jiajie He, Yuanhong Jiang, Xintong Chen +2Human Behavior SimulationUser Simulation

    Hithink Research · McMaster University · Nanyang Technological University

  8. DeltaTrace: Efficient Signed Attribution for Reasoning Language Models

    Oct 19, 2026Chen Liang, Daoping Wu, Donghua Yang +4Feature AttributionLLM Interpretability

    Harbin Institute of Technology · Zhejiang Lab

  9. 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 ReasoningFaithfulness of Language Model Explanations

    Columbia University · Second Look Research

  10. The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls

    Oct 16, 2026Lucas Resck, Jingyi Sun, Qianli Wang +2CoT FaithfulnessFaithfulness of Language Model Reasoning

    Language Technology Lab, University of Cambridge · University of Copenhagen · Technische Universität Berlin +1

  11. When Can You Trust an Agent's Own Verifier? Stress-Testing Counterfactual Rationale Verification Under Search Pressure and Oracle Access

    Oct 16, 2026Jonghyun Lee, Moonsu Kim, Sunghwan ParkLLM Agent VerificationAutomated Agent Evaluation

    Yonsei University

  12. Mitigating Demographic Disparities in Explanation-Human Alignment via Rationale Regularization

    Oct 15, 2026Suryansh Talukdar, Taha Sarwat, Jonathan RusertDemographic Bias in Language ModelsFaithfulness of Language Model Explanations

    Purdue University Fort Wayne

  13. On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination

    Oct 13, 2026Kevin Yandoka DenamganaïLanguage Model AuditingAutoencoders

  14. FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation

    Oct 13, 2026Cecelia Soh, Jun Hu, Yuan Li +6Faithfulness of Language Model ExplanationsLLMs for Graph Learning

    National University of Singapore · Hefei University of Technology · ByteDance Inc. +1

  15. Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features

    Oct 13, 2026Samuel Xie, Noura Al-MoubayedFaithfulness of Language Model ExplanationsSHAP Feature Attribution

    Independent · Durham University

  16. Structural Chain-of-Thought: Reasoning with Executable Computational Graphs

    Oct 10, 2026Petr Senatorov, Karim Vafin, Elena Tutubalina +1LLM Reasoning with GraphsEfficient Language Model Reasoning

    MIPT · AIRI

  17. Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness

    Oct 8, 2026Saisab Sadhu, Shreeyans Arora, Pratinav SethFaithfulness of Language Model ExplanationsLLM Auditing

    Lexsi Labs

  18. Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

    Oct 2, 2026Samuel Lewis-Lim, Xingwei Tan, Mario Sanger +2Faithfulness of Language Model ReasoningEfficient Language Model Reasoning

    School of Computer Science, University of Sheffield · AstraZeneca

  19. MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations

    Oct 1, 2026Yuyang Cheng, Raghav Kaushik Ravi, Srivarshinee Sridhar +3Explainable Artificial IntelligenceFaithfulness of Language Model Explanations

    University of Virginia · Vellore Institute of Technology · Indian Institute of Technology, Patna

  20. A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined

    Oct 1, 2026Zhangshu Joshua Jiang, Zina Ibrahim, James T. TeoFaithfulness of Language Model ExplanationsTemporal Reasoning in Language Models

    DRIVE-Health CDT Department of Biostatistics and Health Informatics Institute of Psychiatry, Psychology and Neuroscience King’s College London London, UK · Cleveland Clinic London London, UK

  21. How the Audit Rule Shapes Faithful Factor Explanations in LLMs

    Oct 1, 2026Taolin Zhang, Hanyu Wang, Jiuheng Wan +2Counterfactual ExplanationsFaithfulness of Language Model Explanations

    Hefei University of Technology · East China Normal University · Alibaba Cloud Computing

  22. When Do Biological Reasoning Models Use Their Biological Inputs?

    Oct 1, 2026Ada Fang, Nikitha Thoduguli, Lukas Fesser +3Faithfulness of Language Model ExplanationsCausal Interventions in Language Models

    Harvard University · Massachusetts Institute of Technology

  23. Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

    Sep 30, 2026Yihuai Hong, Shauli Ravfogel, Chen Zhao +1CoT FaithfulnessFaithfulness of Language Model Explanations

    New York University · NYU Shanghai

  24. Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions

    Sep 30, 2026Sujung Kim, Seung Hwan Cho, Sangjin Park +1Numerical Reasoning in Language ModelsFaithfulness of Language Model Explanations

    Department of Industrial Data Engineering, Hanyang University, Republic of Korea · School of Interdisciplinary Industrial Studies, Hanyang University, Republic of Korea

  25. Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces

    Sep 29, 2026Ratish Puduppully, Pranabendu Misra, Paarth Iyer +3Faithfulness of Language Model ExplanationsCoT Evaluation

    IT University of Copenhagen · Chennai Mathematical Institute · Indian Institute of Technology Jammu +1

  26. Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?

    Sep 28, 2026Li Zhang, Chuqin Geng, Mark Zhang +4Faithfulness of Language Model ExplanationsMechanistic Interpretability

    University of Toronto · McGill University · Tsinghua University

  27. When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment

    Sep 28, 2026Zhaohan Zhang, Junjie Liu, Chengzhengxu Li +6Faithfulness of Language Model ExplanationsConfidence Estimation in Language Models

    Queen Mary University of London · Tongyi Lab, Alibaba Group · Xi’an Jiaotong University

  28. Understanding Confabulation and Rethinking Reconstruction in Activation Explanations

    Sep 27, 2026Gert Lek, Zixuan Xia, Pin-Yu Chen +1Transformer InterpretabilityFaithfulness of Language Model Explanations

    Universit´e de Neuchˆatel · Universität Bern · IBM Research +1

  29. CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification

    Sep 27, 2026Massa Baali, Sarthak Bisht, Ziyue Qiu +3Speaker VerificationFaithfulness of Language Model Explanations

    Carnegie Mellon University, USA

  30. Right Answer, Wrong Reason: Accuracy, Consistency, and Consensus Are Misleading Indicators of LLM Faithfulness in Clinical Decision Support

    Sep 26, 2026Bharath Kumar Bolla, Chaitali Deb Purkayastha, Vishnu Surya Reddy NandiFaithfulness of Language Model ExplanationsClinical Language Model Evaluation

    Institute of Product Leadership, Bengaluru, India · Independent Researcher, Bengaluru, India · Amazon, Inc, Seattle, USA