Saved in:
Bibliographic Details
Main Authors: Garg, Madhav Krishan, Prasad, Tejash, Singhal, Tanmay, Kirtani, Chhavi, Mandal, Murari, Kumar, Dhruv
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.11736
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918033058955264
author Garg, Madhav Krishan
Prasad, Tejash
Singhal, Tanmay
Kirtani, Chhavi
Mandal, Murari
Kumar, Dhruv
author_facet Garg, Madhav Krishan
Prasad, Tejash
Singhal, Tanmay
Kirtani, Chhavi
Mandal, Murari
Kumar, Dhruv
contents The escalating volume of academic research, coupled with a shortage of qualified reviewers, necessitates innovative approaches to peer review. In this work, we propose: 1. ReviewEval, a comprehensive evaluation framework for AI-generated reviews that measures alignment with human assessments, verifies factual accuracy, assesses analytical depth, identifies degree of constructiveness and adherence to reviewer guidelines; and 2. ReviewAgent, an LLM-based review generation agent featuring a novel alignment mechanism to tailor feedback to target conferences and journals, along with a self-refinement loop that iteratively optimizes its intermediate outputs and an external improvement loop using ReviewEval to improve upon the final reviews. ReviewAgent improves actionable insights by 6.78% and 47.62% over existing AI baselines and expert reviews respectively. Further, it boosts analytical depth by 3.97% and 12.73%, enhances adherence to guidelines by 10.11% and 47.26% respectively. This paper establishes essential metrics for AIbased peer review and substantially enhances the reliability and impact of AI-generated reviews in academic research.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11736
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReviewEval: An Evaluation Framework for AI-Generated Reviews
Garg, Madhav Krishan
Prasad, Tejash
Singhal, Tanmay
Kirtani, Chhavi
Mandal, Murari
Kumar, Dhruv
Computation and Language
Artificial Intelligence
The escalating volume of academic research, coupled with a shortage of qualified reviewers, necessitates innovative approaches to peer review. In this work, we propose: 1. ReviewEval, a comprehensive evaluation framework for AI-generated reviews that measures alignment with human assessments, verifies factual accuracy, assesses analytical depth, identifies degree of constructiveness and adherence to reviewer guidelines; and 2. ReviewAgent, an LLM-based review generation agent featuring a novel alignment mechanism to tailor feedback to target conferences and journals, along with a self-refinement loop that iteratively optimizes its intermediate outputs and an external improvement loop using ReviewEval to improve upon the final reviews. ReviewAgent improves actionable insights by 6.78% and 47.62% over existing AI baselines and expert reviews respectively. Further, it boosts analytical depth by 3.97% and 12.73%, enhances adherence to guidelines by 10.11% and 47.26% respectively. This paper establishes essential metrics for AIbased peer review and substantially enhances the reliability and impact of AI-generated reviews in academic research.
title ReviewEval: An Evaluation Framework for AI-Generated Reviews
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.11736