safety
The Abstract Gave the Author Away
Language models narrowed anonymous papers to likely experts using conceptual signatures even without citation or style cues.
Summary
Language models narrowed anonymous papers to likely experts using conceptual signatures even without citation or style cues.
Using titles and abstracts published after model training and five-person expert candidate pools, the authors report that language models concentrated authorship guesses more effectively than human readers. The effect persisted after removing stylistic and bibliographic cues, suggesting problem choice and framing can compromise double-blind review.
Why it matters
Language models narrowed anonymous papers to likely experts using conceptual signatures even without citation or style cues.
Limits and context
No additional limitation was separately recorded.
Key claims
Language models narrowed anonymous papers to likely experts using conceptual signatures even without citation or style cues.
Evidence: source-2026-08-09-017
Sources
- arXiv preprint 2608.05157arXiv · primary research
Corrections
No corrections have been recorded for this story.