Large language models eroding science understanding: an experimental study
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910174383439872 |
|---|---|
| author | Collins, Harry Grote, Hartmut Newbury, Paul Sutton, Patrick Thorne, Simon |
| author_facet | Collins, Harry Grote, Hartmut Newbury, Paul Sutton, Patrick Thorne, Simon |
| contents | This paper is under review in AI and Ethics 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25639 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Large language models eroding science understanding: an experimental study Collins, Harry Grote, Hartmut Newbury, Paul Sutton, Patrick Thorne, Simon Computers and Society Artificial Intelligence This paper is under review in AI and Ethics 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. |
| title | Large language models eroding science understanding: an experimental study |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2604.25639 |