PaperGuard benchmark shows multimodal AI reviewers are vulnerable to domain-specific attacks on text and figures and proposes a chunk-based embedding defense.
A Dataset of Peer Reviews ( P eer R ead): Collection, Insights and NLP Applications
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 5years
2026 5verdicts
UNVERDICTED 5roles
dataset 1polarities
use dataset 1representative citing papers
FirstPass curates multi-round peer review dialogues from Nature Communications and fine-tunes Qwen2.5-7B to predict Standard vs Extended revision cycles at 80.5% accuracy after applying response-only loss masking.
Introduces RevCI benchmark and IMPACT multi-agent framework for evidence-level contradiction detection and graded intensity scoring in peer reviews, distilled into efficient TIDE model.
Peer review reports in AI conferences have grown longer and more standardized after LLMs, with increased emphasis on surface-level clarity and summaries at the expense of deeper critiques on originality and replicability.
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.
citing papers explorer
-
Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review
PaperGuard benchmark shows multimodal AI reviewers are vulnerable to domain-specific attacks on text and figures and proposes a chunk-based embedding defense.
-
FirstPass: Grounding AI Scientific Judgment in Multi-Round Editorial Outcomes
FirstPass curates multi-round peer review dialogues from Nature Communications and fine-tunes Qwen2.5-7B to predict Standard vs Extended revision cycles at 80.5% accuracy after applying response-only loss masking.
-
When Reviews Disagree: Fine-Grained Contradiction Analysis in Scientific Peer Reviews
Introduces RevCI benchmark and IMPACT multi-agent framework for evidence-level contradiction detection and graded intensity scoring in peer reviews, distilled into efficient TIDE model.
-
Impact of large language models on peer review opinions from a fine-grained perspective: Evidence from top conference proceedings in AI
Peer review reports in AI conferences have grown longer and more standardized after LLMs, with increased emphasis on surface-level clarity and summaries at the expense of deeper critiques on originality and replicability.
-
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.