ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
ActReview post-trains Qwen3-8B-Base on OpenReview rebuttals to generate actionable peer-review feedback with grounded revision suggestions, benchmarked on 1,000 curated instances.
The paper defines Actionable Peer-review Generation as diagnostic claim generation plus revision suggestion generation and introduces ActReview, a rebuttal-guided post-training framework. From OpenReview review-rebuttal threads the authors build ActReview-40K, aligning reviewer weaknesses with author responses grounded in localized paper evidence, and post-train Qwen3-8B-Base with multi-task SFT followed by GRPO using weakness-specific rubric rewards. They also release ActReview-Bench, a human-curated 1,000-instance benchmark, on which 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 but identifies a remaining gap in technical accuracy.
- ActReview-40K built from OpenReview review-rebuttal threads with grounded evidence
- Qwen3-8B-Base post-trained via SFT then GRPO with rubric rewards
- ActReview-Bench provides 1,000 human-curated evaluation instances
- Outperforms prior review-generation models on actionability and grounding
- Organizations
- OpenReview
- AI models
- Qwen3-8B-BaseActReview
From the original article
1 min read at huggingface.co
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.
By Yiling Ma, Yilun Zhao, Sihong Wu · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.