一项预印本测试 15 个大语言模型对临床试验论文中植入方法学错误的检出能力，在原始报告上得分 53% 至 96%，未受训人工审稿人平均为 27%。研究在 2026 年发表的 58 项随机临床试验上重复测试，模型得分 58% 至 99%，开源权重模型为 66% 至 89%，Claude Opus 5.5 以 99% 最高。
这项预印本用植入错误和 2026 年新试验对比 15 个模型与人工审稿，给出了可对照的检出率与耗时差异。
AI now catches far more errors in clinical trial papers than human peer reviewers: all 15 models tested scored 53% to 96% on planted errors, while untrained human reviewers averaged just 27%.
The result held on 58 new trials published in 2026, so the models weren’t simply recalling old papers they had seen in training; Claude Opus 5.5 scored highest at 99%.
Humans miss the errors that most change a trial’s meaning, catching text-table contradictions only 7% of the time, and they take 5 to 8.5 hours per review against AI’s 1.4 to 16.3 minutes.
Lots of debate this week on whether journals should ban AI in peer review. We actually tested this in our new preprint, and the results were pretty clear to me. For context, I've reviewed for most of the big journals and evaluated 1,000 human reviews as an editor. I love to read and evaluate science. TLDR: From now on I won't do any peer review without AI. For clinical trials, I'd even call human-only review dangerous 🧵在 X 查看被引用的帖子
来源：Rohan Paul · x.com