mlsanityData to 7 Oct 2026

From Plausible to Actionable: A Position on LLM Self-Explanations

arXiv 2607.15957 ↗First posted 17 Jul 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior. However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness. Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 77 references that are in the map. First posted on arXiv 17 Jul 2026.

Builds on

43 of 77 references.

References · 43

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  3. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  4. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 651
  5. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  6. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  7. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 415
  8. 2024Self-Preference Bias in LLM-as-a-Judgecited by 248
  9. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 189
  10. 2020Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AIcited by 166
  11. 2024ProSA: Assessing and Understanding the Prompt Sensitivity of LLMscited by 145
  12. 2024Does Prompt Formatting Have Any Impact on LLM Performance?cited by 132
31 more
  1. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  2. 2023Faithfulness Tests for Natural Language Explanationscited by 107
  3. 2024Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Modelscited by 104
  4. 2024Are self-explanations from Large Language Models faithful?cited by 101
  5. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  6. 2024Sycophancy in Large Language Models: Causes and Mitigationscited by 97
  7. 2023Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanationscited by 90
  8. 2024What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineeringcited by 88
  9. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 85
  10. 2020Aligning Faithful Interpretations with their Social Attributioncited by 79
  11. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 77
  12. 2023On Measuring Faithfulness or Self-consistency of Natural Language Explanationscited by 71
  13. 2025Are DeepSeek R1 And Other Reasoning Models More Faithful?cited by 69
  14. 2024Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perceptioncited by 55
  15. 2025When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Modelscited by 46
  16. 2024Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statementscited by 33
  17. 2024Reasoning Robustness of LLMs to Adversarial Typographical Errorscited by 31
  18. 2024Properties and Challenges of LLM-Generated Explanationscited by 24
  19. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 24
  20. 2025How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencodingcited by 19
  21. 2025Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missingcited by 14
  22. 2024Evaluating Human Alignment and Model Faithfulness of LLM Rationalecited by 12
  23. 2026A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behaviorcited by 12
  24. 2024Large Language Models Cannot Explain Themselvescited by 11
  25. 2025Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?cited by 8
  26. 2026Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancycited by 7
  27. 2026When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Makingcited by 2
  28. 2024User Preferences for Large Language Model versus Template-Based Explanations of Movie Recommendations: A Pilot Studycited by 1
  29. 2025Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibilitycited by 1
  30. 2026Evaluating the False Trust Engendered by LLM Explanationscited by 1
  31. 2026Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detectioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations
  2. 2025LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
  3. 2024Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains
  4. 2025Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
  5. 2025Can LLMs Explain Themselves Counterfactually?
  6. 2025Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models
  7. 2025Increasing AI Explainability by LLM Driven Standard Processes
  8. 2026What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs