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.
Llm-reval: Can we trust llm reviewers yet?
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
FactReview extracts claims from ML papers, positions them via literature retrieval, and verifies them through code execution, labeling each as Supported, Partially supported, or In conflict, as shown in a CompGCN case study.
Numerical scores predict ICLR acceptance at 91% accuracy while review text reaches only 81%, because politeness makes rejected papers' reviews contain more positive than negative words.
A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.
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.
-
FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification
FactReview extracts claims from ML papers, positions them via literature retrieval, and verifies them through code execution, labeling each as Supported, Partially supported, or In conflict, as shown in a CompGCN case study.
-
Decoupling Scores and Text: The Politeness Principle in Peer Review
Numerical scores predict ICLR acceptance at 91% accuracy while review text reaches only 81%, because politeness makes rejected papers' reviews contain more positive than negative words.
-
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.