用大模型精准识别边缘论文，高效分配额外审稿资源。
Allocate Marginal Reviews to Borderline Papers Using LLM Comparative Ranking
- 基于大模型对比排序预判边缘论文，无需人工审稿即可定位
- 在3~4篇基础审稿外，仅对边缘论文追加1份审稿，提升效率
- 方法可直接用于会议审稿系统，适合追求公平高效的学术组织
本文主张大型机器学习会议应将有限的额外审稿资源优先分配给接近录用边界的论文，而非通过随机或关联性启发法平均分配。提出一种基于大模型的对比排序方法（通过成对比较与Bradley-Terry模型），在人工审稿前预判边缘论文集合，并在分配时动态决定哪些论文获得额外评审（如第4或第5份）。以会议设定的最低审稿数（如3或4）为信号，仅对符合阈值的论文增加审查，不依赖人类评分，也不使用大模型输出直接决定录用。提供预期影响计算框架，基于预测与真实边缘集重叠率（ρ）和边界处额外审稿增量价值（Δ），并给出可回溯的代理指标估算这两个参数。
原文摘要 · Abstract (English)
This paper argues that large ML conferences should allocate marginal review capacity primarily to papers near the acceptance boundary, rather than spreading extra reviews via random or affinity-driven heuristics. We propose using LLM-based comparative ranking (via pairwise comparisons and a Bradley--Terry model) to identify a borderline band \emph{before} human reviewing and to allocate \emph{marginal} reviewer capacity at assignment time. Concretely, given a venue-specific minimum review target (e.g., 3 or 4), we use this signal to decide which papers receive one additional review (e.g., a 4th or 5th), without conditioning on any human reviews and without using LLM outputs for accept/reject. We provide a simple expected-impact calculation in terms of (i) the overlap between the predicted and true borderline sets ($ρ$) and (ii) the incremental value of an extra review near the boundary ($Δ$), and we provide retrospective proxies to estimate these quantities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。