从貌似合理到切实可行：关于LLM自我解释的立场

Computer Science > Computation and Language arXiv:2607.15957 (cs) [Submitted on 17 Jul 2026 (v1), last revised 4 Sep 2026 (this version, v2)] Title:From Plausible to Actionable: A Position on LLM Self-Explanations Authors:Elize Herrewijnen, Benedetta Muscato, Gizem Gezici, Fosca Giannotti View a PDF of the paper titled From Plausible to Actionable: A Position on LLM Self-Explanations, by Elize Herrewijnen and 3 other authors View PDF HTML (experimental) Abstract: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 this http URL, 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. Comments: 5 pages Subjects: Computation and Language (cs.CL) Cite as: arXiv:2607.15957 [cs.CL] (or arXiv:2607.15957v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2607.15957 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Benedetta Muscato - [view email] [v1] Fri, 17 Jul 2026 13:44:19 UTC (53 KB) [v2] Fri, 4 Sep 2026 13:21:21 UTC (133 KB) Full-text links: Access Paper: View a PDF of the paper titled From Plausible to Actionable: A Position on LLM Self-Explanations, by Elize Herrewijnen and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-07 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)