当偏见伪装成真相：伪相关如何削弱大语言模型中的幻觉检测

Computer Science > Computation and Language arXiv:2511.07318 (cs) [Submitted on 10 Nov 2025 (v1), last revised 11 Sep 2026 (this version, v3)] Title:When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs Authors:Shaowen Wang, Yiqi Dong, Ruinian Chang, Tansheng Zhu, Yuebo Sun, Kaifeng Lyu, Jian Li View a PDF of the paper titled When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs, by Shaowen Wang and 6 other authors View PDF HTML (experimental) Abstract:Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical yet previously underexplored class of hallucinations driven by spurious correlations -- superficial but statistically prominent associations between features (e.g., surnames) and attributes (e.g., nationality) present in the training data. We demonstrate that these spurious correlations induce hallucinations that are confidently generated, immune to model scaling, evade current detection methods, and persist even after refusal fine-tuning. Through systematically controlled synthetic experiments and empirical evaluations on state-of-the-art open-source and proprietary LLMs (including GPT-5), we show that existing hallucination detection methods, such as confidence-based filtering and inner-state probing, fundamentally fail in the presence of spurious correlations. Our theoretical analysis further elucidates why these statistical biases intrinsically undermine confidence-based detection techniques. Our findings thus emphasize the urgent need for new approaches explicitly designed to address hallucinations caused by spurious correlations. Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2511.07318 [cs.CL] (or arXiv:2511.07318v3 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2511.07318 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Shaowen Wang [view email] [v1] Mon, 10 Nov 2025 17:19:27 UTC (7,419 KB) [v2] Fri, 21 Nov 2025 11:45:34 UTC (9,377 KB) [v3] Fri, 11 Sep 2026 10:08:58 UTC (9,359 KB) Full-text links: Access Paper: View a PDF of the paper titled When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs, by Shaowen Wang and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2025-11 Change to browse by: cs cs.AI cs.LG 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?)