Faithfulness of Language Model Explanations

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

122 papers20 papers in the last four weeks, down 23% on the four weeks before. 0.2% of all new papers.

  1. Auditing black-box clinical prediction models with a large language model through queries alone: a blinded test with planted flaws

    Nov 18, 2026Zhiyu Liu, Xinyu YangBlack-Box Model AuditingLLM Auditing

  2. Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests

    Nov 16, 2026Arunkumar VAlgorithmic RecourseFaithfulness of Language Model Explanations

  3. Evaluating and Improving Natural Language Autoencoders

    Nov 14, 2026Marco Bazzani, Dan MossingAutoencodersNeural Network Interpretability

  4. DECODE: Diagnosing Interpretability Failures in Automated Interpretation Process

    Nov 13, 2026Dohyun Kim, Jaeung Lee, Donghee Hong +1Automated InterpretabilityLLM Interpretability

  5. From Counterfactual Edits to Human Narratives: LLM-Driven Interpretations for Recommender System Explanations

    Nov 10, 2026Vojtech Cahlik, Amir Reza Mohammadi, Rodrigo Alves +2Explainable RecommendationCounterfactual Explanations

  6. When Reasoning looks like Hidden Understanding: How Chain-of-Thought Fosters Anthropomorphism, Perceptions of Epistemic Superiority, and Cognitive Deference

    Nov 10, 2026Oliver Lack, Lana Tikhomirov, Humphrey Thompson +2Anthropomorphism in AICoT Reasoning

  7. Large Language Model Explainability for Planning Lunar Rover Trajectories under Uncertainty

    Nov 9, 2026Michelle Ho, Maximilian Adang, Zachary Booth +4Explainable Motion PlanningFaithfulness of Language Model Explanations

  8. Fairness in Explainable AI Narratives: Decomposing Social Disparities in LLM-Generated Explanations

    Nov 9, 2026Wannes Van den Bulck, Sofie Goethals, David MartensSocial Bias in Language ModelsFaithfulness of Language Model Explanations

  9. Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits

    Nov 3, 2026Teerawat Tongloy, Jiraporn Pongsopa, Rangsan JomtarakQuantum TransformersFaithfulness of Language Model Explanations

  10. Evolving Explanations: Complexity-Adaptive Refinement of Faithful Explanations for Symbolic Regression

    Nov 2, 2026Elisabeth Mayrhuber, Ting Hu, Stephan WinklerExplainable Artificial IntelligenceFaithfulness of Language Model Explanations

  11. A Bounded Evaluation Protocol for Representational Systematicity

    Nov 1, 2026Boyu Cao, Wenshuo WangExplainability EvaluationFaithfulness of Language Model Explanations

  12. SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI

    Oct 30, 2026Van Bach Nguyen, Qianli Wang, Nils Feldhus +2Explainable Artificial IntelligenceTool-Augmented Language Model Agents

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

    Oct 27, 2026Haokun Wen, Xuemeng Song, Mong-Li Lee +1Preference Learning for LLMsAutomated Fact-Checking

  14. Faithful Explanations under Missing Modalities in Multimodal Dementia Prognosis

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

  15. 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

  16. 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

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

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

  18. DeltaTrace: Efficient Signed Attribution for Reasoning Language Models

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

  19. 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

  20. 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