大型语言模型侵蚀科学理解：一项关于错位对齐的实证研究

Computer Science > Computers and Society arXiv:2604.25639 (cs) [Submitted on 28 Apr 2026 (v1), last revised 17 Sep 2026 (this version, v2)] Title:Large language models eroding science understanding: an empirical study of malignment Authors:Harry Collins, Hartmut Grote, Paul Newbury, Patrick Sutton, Simon Thorne View a PDF of the paper titled Large language models eroding science understanding: an empirical study of malignment, by Harry Collins and 4 other authors View PDF Abstract:This paper is accepted and in press for AI and Ethics. This paper includes the supplementary data file at the end of the manuscript. This study examines whether large language models (LLMs) can reliably answer scientific questions and demonstrates how easily they can be influenced by fringe scientific material. The authors modified custom LLMs to prioritise knowledge in selected fringe papers on the Fine Structure Constant and Gravitational Waves, then compared their responses with those of domain experts and standard LLMs. The altered models produced fluent, convincing answers that contradicted scientific consensus and were difficult for non-experts to detect as misleading. The results show that LLMs are vulnerable to manipulation and cannot replace expert judgment, highlighting risks for public understanding of science and the potential spread of misinformation. Comments: Subjects: Computers and Society (cs.CY); Artificial Intelligence (cs.AI) Cite as: arXiv:2604.25639 [cs.CY] (or arXiv:2604.25639v2 [cs.CY] for this version) https://doi.org/10.48550/arXiv.2604.25639 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Simon Thorne [view email] [via Simon Thorne Dr as proxy] [v1] Tue, 28 Apr 2026 13:39:44 UTC (299 KB) [v2] Thu, 17 Sep 2026 17:06:34 UTC (1,436 KB) Full-text links: Access Paper: View a PDF of the paper titled Large language models eroding science understanding: an empirical study of malignment, by Harry Collins and 4 other authors View PDF view license Current browse context: cs.CY new | recent | 2026-04 Change to browse by: cs cs.AI 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?)