Presentation-only revisions guided by AI feedback can boost AI reviewer scores by over 1 point on average with 75% success rate across tested systems.
Reviewrl: Towards automated scientific review with rl.arXiv preprint arXiv:2508.10308, 2025
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
LLMs overrate weak papers, diverge from humans on criteria like clarity and reproducibility, write longer less diverse reviews, and remain vulnerable to prompt injection attacks that can boost low-scoring papers to acceptance levels.
citing papers explorer
-
No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions
Presentation-only revisions guided by AI feedback can boost AI reviewer scores by over 1 point on average with 75% success rate across tested systems.