Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• RbtAct uses rebuttals as implicit supervision to directly optimize a feedback generator for actionability.method 95%
• The paper introduces a new task called perspective-conditioned segment-level review feedback generation.method 95%
• The paper builds a large dataset named RMR-75K that maps review segments to rebuttal segments with perspective labels and impact categories.method 95%
• RbtAct shows consistent gains in actionability and specificity over strong baselines in experiments with human experts and LLM-as-a-judge.result 90%
• Many AI-generated peer reviews are superficial and insufficiently actionable, leaving authors without concrete guidance.limitation 85%
• The model is trained with supervised fine-tuning on review segments followed by preference optimization using rebuttal-derived pairs.method 90%
• RbtAct maintains grounding and relevance while improving actionability and specificity.result 85%
• Rebuttals show which reviewer comments led to concrete revisions versus which were only defended.technical 90%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card