Harvard 研究称 Claude Opus 4.8 生成的论文评审在测试指标上优于人类评审

AI 导读

Harvard 研究发现，Claude Opus 4.8 生成的论文评审在作者测试的各项指标上超过最佳人类同行评审。研究使用 rapidPeer 的 134 条评审和 1124 篇论文，由 GPT-5.5 与 3 名前期刊编辑进行盲评；GPT-5.5 在 132 组可判定对比中全部选择 AI 评审，编辑选择 AI 评审的比例为 87%。

正文 · 原文

Massive. New Harvard study finds that AI-written paper reviews now beat the best human peer reviews on every measure the authors tested.

Peer review is slow and often misses errors. Earlier studies concluded AI should only assist human reviewers, not replace them.

They used 134 reviews from rapidPeer, a Harvard service that pays expert reviewers well. Claude Opus 4.8 reviewed the same 1124 papers, and GPT-5.5 plus 3 former journal editors judged the pairs blind.

GPT-5.5 picked the AI review in all 132 decided pairs, and the editors picked it 87% of the time. Only 5.5% of the AI's claims about the paper were wrong, versus 15.9% for the human reviews.

Teams that depend on expert critique can now let AI do the first full review pass, and keep a human for the final decision.