# ActReview：用作者反驳引导训练数据与评分奖励，生成可执行的同行评审意见

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-08 08:00
- AIHOT 分数：33
- AIHOT 链接：https://aihot.news/items/cmtx5710q07ciroedzcr1v0eh
- 原文链接：https://arxiv.org/abs/2609.09076

## AI 摘要

研究团队提出 ActReview，一个以作者反驳（rebuttal）为引导的后训练框架，用于生成可执行的同行评审意见，并拆解为诊断性论断生成与修改建议生成两个子任务。

## 正文

Abstract:As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identifies weaknesses but also guides authors toward concrete revisions. We study this as Actionable Peer-review Generation and decompose it into two subtasks: diagnostic claim generation and revision suggestion generation. We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans. Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can therefore provide latent supervision for revision-oriented feedback. From real review-rebuttal threads on OpenReview, we construct ActReview-40K by aligning reviewer weaknesses with author responses and grounding the resulting feedback in localized paper evidence. We post-train Qwen3-8B-Base with multi-task supervised fine-tuning followed by GRPO using candidate-aware, weakness-specific rubric rewards. We also introduce ActReview-Bench, a human-curated benchmark of 1,000 instances for evaluating diagnostic quality and revision usefulness. Experiments show that ActReview outperforms prior specialized review-generation models on actionability and grounding while remaining competitive with strong prompt-based LLMs. Human evaluation confirms improved revision usefulness while revealing a remaining gap in technical accuracy, and additional analyses support generalization to held-out papers and robustness across independent judges.

Comments:

Subjects: Computation and Language (cs.CL)

Cite as: arXiv:2609.09076 [cs.CL]

(or arXiv:2609.09076v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.09076

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yiling Ma [

Tue, 8 Sep 2026 17:30:16 UTC (3,356 KB)

Access Paper:

Current browse context:

References & Citations

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article