Megadose AI progress, ranked and analyzed.

ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation

· ArXiv · AI/CL/LG ·
ActReview uses author rebuttals as supervision for review feedback that points to concrete paper revisions.

The paper frames the task as generating both diagnostic claims and revision suggestions. Its ActReview-40K dataset aligns reviewer weaknesses with author responses from OpenReview threads, grounded in localized evidence from the paper. The authors post-train Qwen3-8B-Base with supervised fine-tuning and GRPO using weakness-specific rubric rewards. They report stronger actionability and grounding than prior specialized review-generation models, while human evaluation still finds a gap in technical accuracy. ArXiv · AI/CL/LG's note

score 4

Categories: Research