ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
Updated 2 h ago · first seen 11 Sept 2026
paper_01M294WYEG967ANKFJX5ZKK6YY
- Published
- 8 Sept 2026
- T2 · 4 h ago
- arXiv
- 2609.09076
- T2 · 4 h ago
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.
Authors 6
Yiling Ma, Yilun Zhao, Sihong Wu, Ziyu Chen, Manasi Patwardhan, Arman Cohan
Specification
- Official page
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- arXiv id
- 2609.09076
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Github repo
- Yiling-Ma/ActReview
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Hf paper url
- https://huggingface.co/papers/2609.09076
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Github stars
- 0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hf comments
- 1
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Upvotes
- 0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Published
- 8 Sept 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
11
Source tiers
T211
Freshest observation
2 h ago
Conflicts
None
No models linked to this paper yet.
No relations recorded.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Abstract
Abstractabstract1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 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. | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
- New paperPaperActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
New paper: ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
huggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/papers | listing | T2· Quality secondary | 2 h ago | 3 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.