LLMs catch methodological errors human peer review misses in clinical trials
rohanpaul_ai · x · 2026-10-29
A medRxiv preprint: in an earlier experiment, untrained human reviewers achieved a mean 27% major-error detection score on three error-seeded randomized clinical trial reports. This study tested 15 LLMs (including four open-weight models) on the same task, repeating it on 58 RCTs published in 2026 (all eligible phase 3 trials) to guard against memorization — 1,796 reviews scored by two blinded LLM judges. Results indicate LLMs detect methodological errors that human peer review misses.
More from Research
- Researcher: one steering vector can make an RLHF model shout slurs, no prompt can match it — voooooogel · 2026-10-29
- OpenAI's math argument still unverified: no expert has publicly assessed it — maier_ak · 2026-10-29
- OpenAI's Lean-formalized conjectures await expert review; firm calls it raw data — maier_ak · 2026-10-29
- OpenAI model's Lean-verified manuscript targets local smoothing and Kakeya conjectures — maier_ak · 2026-10-29
- OpenAI model claims 59-page Lean proof of local smoothing and Kakeya in every dimension — maier_ak · 2026-10-29
- TTME beats test-time training on math discovery with 84% fewer FLOPs — rohanpaul_ai · 2026-10-29