LLM 反事实自我解释的实证研究

Computer Science > Computation and Language arXiv:2609.17119 (cs) [Submitted on 15 Sep 2026] Title:An Empirical Study of Counterfactual Self-Explanations in LLMs Authors:Giannis Kalyvas, Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Vassilis Lyberatos, Giorgos Stamou View a PDF of the paper titled An Empirical Study of Counterfactual Self-Explanations in LLMs, by Giannis Kalyvas and 4 other authors View PDF HTML (experimental) Abstract:Large language models can easily generate explanations for their own outputs, but such self-explanations are not necessarily faithful to the model's behavior. We study this issue through counterfactual self-explanations, where a model minimally edits an input so that its own prediction changes. Across sentiment analysis and natural language inference, we evaluate ten instruction-tuned models from the LLaMA-3 and Qwen-2.5 families, measuring faithfulness, minimality, and alignment with human-annotated rationales. Our results show that model scale is the strongest determinant of explanation quality: larger models are substantially more likely to generate counterfactuals that flip their own predictions and target decision-relevant evidence. In contrast, the rationale-guided condition produces edit-minimal counterfactuals that are also more human-aligned. However, it does not consistently improve faithfulness. Overall, counterfactual self-explanations can provide useful behavioral evidence about model decisions, but their reliability depends strongly on model capacity and should be empirically validated rather than assumed. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2609.17119 [cs.CL] (or arXiv:2609.17119v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2609.17119 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Vassilis Lyberatos [view email] [v1] Tue, 15 Sep 2026 12:47:22 UTC (1,153 KB) Full-text links: Access Paper: View a PDF of the paper titled An Empirical Study of Counterfactual Self-Explanations in LLMs, by Giannis Kalyvas and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-09 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?)