arXiv cs.AI· Xuanyou Liu, Ziyang Guo, Jason Hartline, Jessica Hullman·· 13 小时前AI 评分31
用学习到的检查清单降低科学同行评审中的“审稿人抽签效应”
Learning Checklists to Reduce Lottery Effects in Scientific Peer Review
AI 导读
研究提出从历史评审语料中学习批评检查清单，以降低“审稿人抽签误差”。方法生成原子评审主张空间的粗化检查清单树，并选出审稿人相关一致性最高的粗化版本，用 LLM 辅助流程在 NeurIPS 2021 和 ICLR 2022 数据上验证。
正文 · 原文
Abstract:Reviewer lottery error describes error due to a small set of peer reviews attending to only some of the issues with a paper that a larger pool of eligible reviewers would raise. We show this error can be reduced by surfacing a checklist of criticisms learned from a historical review corpus. Our approach generates a tree of checklists representing coarsenings of the atomic review claim space, then selects the coarsening that maximizes a theoretically-motivated measure of correlated agreement among reviewers. We realize this approach with an LLM-assisted pipeline and test it on NeurIPS 2021 and ICLR 2022 review data. In simulated review with LLM reviewers, the learned checklist reduces the mean squared error (MSE) of a three reviewer committee by 58% on NeurIPS and 21% on ICLR, and on both venues the checklist with the highest correlated agreement has the lowest error for committees of three or more. In a human study with 20 participants, the learned NeurIPS checklist lowers the MSE of a paper ranking, measured against the NeurIPS 2021 order, from 0.48 to 0.22.
| Subjects: | Digital Libraries (cs.DL); Artificial Intelligence (cs.AI); Applications (stat.AP) |
| Cite as: | arXiv:2610.28666 [cs.DL] |
| (or arXiv:2610.28666v1 [cs.DL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28666 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jessica Hullman [view email]
[v1]
Wed, 14 Oct 2026 21:22:33 UTC (284 KB)
来源：arXiv cs.AI · arxiv.org