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. Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models

    Mar 16, 2026Francesco Sovrano, Alberto BacchelliFaithfulness of Language Model ExplanationsRetrieval-Augmented Generation

    Collegium Helveticum, ETH Zurich, Zurich, Switzerland · University of Zurich, Zurich, Switzerland

  2. Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning

    Mar 14, 2026Halimat Afolabi, Zainab Afolabi, Elizabeth Friel +13Faithfulness of Language Model ExplanationsMedical LLMs

    Stratified Precision, United Kingdom · Harvard Medical School, United States · Imperial College London, United Kingdom +3

  3. Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation

    Mar 10, 2026Eeham Khan, Luis Rodriguez, Marc QueudotRAG Citation FaithfulnessRetrieval-Augmented Generation

    Concordia University, Montréal, QC, Canada · Centre de recherche informatique de Montréal (CRIM), Montréal, QC, Canada

  4. PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations

    Mar 6, 2026Vittoria Vineis, Matteo Silvestri, Lorenzo Antonelli +2Explainable Artificial IntelligenceFaithfulness of Language Model Explanations

    Sapienza University of Rome · Syllotips · TellmewAI s.r.l.

  5. Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought

    Mar 5, 2026Siddharth Boppana, Annabel Ma, Max Loeffler +5Faithfulness of Language Model ReasoningLanguage Model Reasoning Evaluation

    Goodfire AI · Harvard University, Cambridge, MA

  6. C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning

    Mar 5, 2026Avni Mittal, Rauno ArikeCoT FaithfulnessLLM-as-a-Judge

  7. Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

    Mar 2, 2026Kyle Cox, Darius Kianersi, Adrià Garriga-AlonsoFaithfulness of Language Model ExplanationsLLM Interpretability

    Independent · Cambridge Boston Alignment Initiative (CBAI)

  8. LLM Self-Explanations Fail Semantic Invariance

    Mar 1, 2026Stefan SzeiderFaithfulness of Language Model ExplanationsLanguage Model Self-Assessment

    Algorithms and Complexity Group, TU Wien, Vienna, Austria

  9. Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models

    Feb 25, 2026Christian Nickel, Laura Schrewe, Florian Mai +1Theory of MindLanguage Model Robustness

    Bonn-Aachen International Center for Information Technology (b-it), University of Bonn · Lamarr Institute for Machine Learning and Artificial Intelligence · Research Center Trustworthy Data Science and Security (RC-Trust), University of Duisburg-Essen

  10. Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision

    Feb 23, 2026Kartik Kuckreja, Parul Gupta, Muhammad Haris Khan +1Deepfake DetectionExplainable Deepfake Detection

    MBZUAI · Monash University *

  11. TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning

    Feb 21, 2026Yujiao YangLLM InterpretabilityFaithfulness of Language Model Explanations

    Dalian University of Technology, Dalian, China

  12. Could Large Language Models work as Post-hoc Explainability Tools in Credit Risk Models?

    Feb 21, 2026Wenxi Geng, Dingyuan Liu, Liya Li +1Explainable Artificial IntelligenceExplainability Evaluation

    Citigroup, Irving, TX, United States · University of North Carolina at Chapel Hill, Chapel Hill, NC, United States · Georgia Institute of Technology, Atlanta, GA, United States +1

  13. Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution

    Feb 18, 2026Nithin Sivakumaran, Shoubin Yu, Hyunji Lee +4CoT FaithfulnessFaithfulness of Language Model Explanations

    UNC Chapel Hill · Cisco · University of Texas at Austin

  14. Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models

    Feb 3, 2026Anish Sathyanarayanan, Aditya Nagarsekar, Aarush RathoreCoT FaithfulnessFaithfulness of Language Model Explanations

    BITS Pilani, K. K. Birla Goa Campus

  15. A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior

    Feb 2, 2026Harry Mayne, Justin Singh Kang, Dewi Gould +3Faithfulness of Language Model ExplanationsLLM Interpretability

    University of Oxford · University of California, Berkeley · Independent +2

  16. LIFT: Likelihood-Based Intervention Faithfulness Training

    Sep 10, 2025Anand Swaroop, Maheep Chaudhary, Kevin Zhu +2CoT FaithfulnessFaithfulness of Language Model Explanations

    Algoverse AI Research

  17. Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations

    Mar 17, 2025Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz +1Faithfulness of Language Model ExplanationsLLM Interpretability

    Google DeepMind · Centre for AI, University College London · Imperial College London +1