Generative Adversarial Reviews: When LLMs Become the Critic

• URL: http://arxiv.org/abs/2412.10415v1
• Date: Mon, 09 Dec 2024 06:58:17 GMT
• Title: Generative Adversarial Reviews: When LLMs Become the Critic
• Authors: Nicolas Bougie, Narimasa Watanabe,
• Abstract summary: We introduce Generative Agent Reviewers (GAR), leveraging LLM-empowered agents to simulate faithful peer reviewers. Central to this approach is a graph-based representation of manuscripts, condensing content and logically organizing information. Our experiments demonstrate that GAR performs comparably to human reviewers in providing detailed feedback and predicting paper outcomes.
• Score: 1.2430809884830318
• License:
• Abstract: The peer review process is fundamental to scientific progress, determining which papers meet the quality standards for publication. Yet, the rapid growth of scholarly production and increasing specialization in knowledge areas strain traditional scientific feedback mechanisms. In light of this, we introduce Generative Agent Reviewers (GAR), leveraging LLM-empowered agents to simulate faithful peer reviewers. To enable generative reviewers, we design an architecture that extends a large language model with memory capabilities and equips agents with reviewer personas derived from historical data. Central to this approach is a graph-based representation of manuscripts, condensing content and logically organizing information - linking ideas with evidence and technical details. GAR's review process leverages external knowledge to evaluate paper novelty, followed by detailed assessment using the graph representation and multi-round assessment. Finally, a meta-reviewer aggregates individual reviews to predict the acceptance decision. Our experiments demonstrate that GAR performs comparably to human reviewers in providing detailed feedback and predicting paper outcomes. Beyond mere performance comparison, we conduct insightful experiments, such as evaluating the impact of reviewer expertise and examining fairness in reviews. By offering early expert-level feedback, typically restricted to a limited group of researchers, GAR democratizes access to transparent and in-depth evaluation.

Related papers

• Aspect-Aware Decomposition for Opinion Summarization [82.38097397662436]
  We propose a modular approach guided by review aspects which separates the tasks of aspect identification, opinion consolidation, and meta-review synthesis. We conduct experiments across datasets representing scientific research, business, and product domains. Results show that our method generates more grounded summaries compared to strong baseline models.
  arXiv  Detail & Related papers  (2025-01-27T09:29:55Z)
• OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews [3.660182910533372]
  OpenReviewer is an open-source system for generating high-quality peer reviews of machine learning and AI conference papers. Llama-OpenReviewer-8B is an 8B parameter language model specifically fine-tuned on 79,000 expert reviews from top ML conferences.
  arXiv  Detail & Related papers  (2024-12-16T16:31:00Z)
• Streamlining the review process: AI-generated annotations in research manuscripts [0.5735035463793009]
  This study explores the potential of integrating Large Language Models (LLMs) into the peer-review process to enhance efficiency without compromising effectiveness. We focus on manuscript annotations, particularly excerpt highlights, as a potential area for AI-human collaboration. This paper introduces AnnotateGPT, a platform that utilizes GPT-4 for manuscript review, aiming to improve reviewers' comprehension and focus.
  arXiv  Detail & Related papers  (2024-11-29T23:26:34Z)
• AgentReview: Exploring Peer Review Dynamics with LLM Agents [13.826819101545926]
  We introduce AgentReview, the first large language model (LLM) based peer review simulation framework. Our study reveals significant insights, including a notable 37.1% variation in paper decisions due to reviewers' biases.
  arXiv  Detail & Related papers  (2024-06-18T15:22:12Z)
• A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligence [55.33653554387953]
  Pattern Analysis and Machine Intelligence (PAMI) has led to numerous literature reviews aimed at collecting and fragmented information. This paper presents a thorough analysis of these literature reviews within the PAMI field. We try to address three core research questions: (1) What are the prevalent structural and statistical characteristics of PAMI literature reviews; (2) What strategies can researchers employ to efficiently navigate the growing corpus of reviews; and (3) What are the advantages and limitations of AI-generated reviews compared to human-authored ones.
  arXiv  Detail & Related papers  (2024-02-20T11:28:50Z)
• Towards Personalized Review Summarization by Modeling Historical Reviews from Customer and Product Separately [59.61932899841944]
  Review summarization is a non-trivial task that aims to summarize the main idea of the product review in the E-commerce website. We propose the Heterogeneous Historical Review aware Review Summarization Model (HHRRS) We employ a multi-task framework that conducts the review sentiment classification and summarization jointly.
  arXiv  Detail & Related papers  (2023-01-27T12:32:55Z)
• Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach [77.61131357420201]
  We conduct a thorough and rigorous study on fairness disparities in peer review with the help of large language models (LMs) We collect, assemble, and maintain a comprehensive relational database for the International Conference on Learning Representations (ICLR) conference from 2017 to date. We postulate and study fairness disparities on multiple protective attributes of interest, including author gender, geography, author, and institutional prestige.
  arXiv  Detail & Related papers  (2022-11-07T16:19:42Z)
• On Faithfulness and Coherence of Language Explanations for Recommendation Systems [8.143715142450876]
  This work probes state-of-the-art models and their review generation component. We show that the generated explanations are brittle and need further evaluation before being taken as literal rationales for the estimated ratings.
  arXiv  Detail & Related papers  (2022-09-12T17:00:31Z)
• Ranking Scientific Papers Using Preference Learning [48.78161994501516]
  We cast it as a paper ranking problem based on peer review texts and reviewer scores. We introduce a novel, multi-faceted generic evaluation framework for making final decisions based on peer reviews.
  arXiv  Detail & Related papers  (2021-09-02T19:41:47Z)
• Can We Automate Scientific Reviewing? [89.50052670307434]
  We discuss the possibility of using state-of-the-art natural language processing (NLP) models to generate first-pass peer reviews for scientific papers. We collect a dataset of papers in the machine learning domain, annotate them with different aspects of content covered in each review, and train targeted summarization models that take in papers to generate reviews. Comprehensive experimental results show that system-generated reviews tend to touch upon more aspects of the paper than human-written reviews.
  arXiv  Detail & Related papers  (2021-01-30T07:16:53Z)
• How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements [8.471274313213092]
  We investigate a growing body of work that seeks to improve recommender systems through the use of review text. Our initial findings reveal several discrepancies in reported results, partly due to copying results across papers despite changes in experimental settings or data pre-processing. Further investigation calls for discussion on a much larger problem about the "importance" of user reviews for recommendation.
  arXiv  Detail & Related papers  (2020-05-25T16:30:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.