An unsupervised likelihood-gain score, computed by comparing a review's probability with and without hints drawn from itself, separates AI-delegated reviews from human or machine-polished reviews and rises as external information is supplied.
What Can We Do to Improve Peer Review in NLP? , booktitle =
7 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
7
Pith papers citing it
2
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Through 27 interviews and a design probe, the study shows area chairs differ substantially in engagement style and are cautiously open to AI assistance that adapts to their workflows.
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.
An audit of 50,289 ICLR papers shows acceptance odds vary up to 8x across topics at equal reviewer scores, indicating scores are not comparable across research areas.
A multi-agent writing tutor for Overleaf that uses 12 agents and an expert skill library to generate inline comments, with a 14-user study reporting 90.6% actionable and 67.5% valid comments that outperform a GPT-5.2 baseline.
NLP researchers should define cognitive terms, temper expectations, and candidly address ethical failures when speaking with the public.
Early citations forecast later citations far better than publication venue does across ACL, PubMed, and arXiv papers.
citing papers explorer
-
How Much Were You Told? Measuring External Information in Peer Reviews
An unsupervised likelihood-gain score, computed by comparing a review's probability with and without hints drawn from itself, separates AI-delegated reviews from human or machine-polished reviews and rises as external information is supplied.
-
Hands-Off or Hands-On? Variation in Area Chair Practices and Implications for AI Support
Through 27 interviews and a design probe, the study shows area chairs differ substantially in engagement style and are cautiously open to AI assistance that adapts to their workflows.
-
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.
-
Reviewer Scores Are Not Comparable Across Research Areas in ML Peer Review
An audit of 50,289 ICLR papers shows acceptance odds vary up to 8x across topics at equal reviewer scores, indicating scores are not comparable across research areas.
-
PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf
A multi-agent writing tutor for Overleaf that uses 12 agents and an expert skill library to generate inline comments, with a 14-user study reporting 90.6% actionable and 67.5% valid comments that outperform a GPT-5.2 baseline.
-
NLP Meets the World: Toward Improving Conversations With the Public About Natural Language Processing Research
NLP researchers should define cognitive terms, temper expectations, and candidly address ethical failures when speaking with the public.
-
Is Peer-Reviewing Worth the Effort?
Early citations forecast later citations far better than publication venue does across ACL, PubMed, and arXiv papers.