Unveiling the Merits and Defects of LLMs in Automatic Review Generation for Scientific Papers

• URL: http://arxiv.org/abs/2509.19326v1
• Date: Sat, 13 Sep 2025 19:15:22 GMT
• Title: Unveiling the Merits and Defects of LLMs in Automatic Review Generation for Scientific Papers
• Authors: Ruochi Li, Haoxuan Zhang, Edward Gehringer, Ting Xiao, Junhua Ding, Haihua Chen,
• Abstract summary: The surge in scientific submissions has placed increasing strain on the traditional peer-review process.<n>We propose a comprehensive evaluation framework that integrates semantic similarity analysis and structured knowledge graph metrics.<n>We construct a benchmark of 1,683 papers and 6,495 expert reviews from ICLR and NeurIPS in multiple years, and generate reviews using five large language models.
• Score: 4.455306283717651
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The surge in scientific submissions has placed increasing strain on the traditional peer-review process, prompting the exploration of large language models (LLMs) for automated review generation. While LLMs demonstrate competence in producing structured and coherent feedback, their capacity for critical reasoning, contextual grounding, and quality sensitivity remains limited. To systematically evaluate these aspects, we propose a comprehensive evaluation framework that integrates semantic similarity analysis and structured knowledge graph metrics to assess LLM-generated reviews against human-written counterparts. We construct a large-scale benchmark of 1,683 papers and 6,495 expert reviews from ICLR and NeurIPS in multiple years, and generate reviews using five LLMs. Our findings show that LLMs perform well in descriptive and affirmational content, capturing the main contributions and methodologies of the original work, with GPT-4o highlighted as an illustrative example, generating 15.74% more entities than human reviewers in the strengths section of good papers in ICLR 2025. However, they consistently underperform in identifying weaknesses, raising substantive questions, and adjusting feedback based on paper quality. GPT-4o produces 59.42% fewer entities than real reviewers in the weaknesses and increases node count by only 5.7% from good to weak papers, compared to 50% in human reviews. Similar trends are observed across all conferences, years, and models, providing empirical foundations for understanding the merits and defects of LLM-generated reviews and informing the development of future LLM-assisted reviewing tools. Data, code, and more detailed results are publicly available at https://github.com/RichardLRC/Peer-Review.

Related papers

• ReviewGuard: Enhancing Deficient Peer Review Detection via LLM-Driven Data Augmentation [3.9199635838637072]
  ReviewGuard is an automated system for detecting and categorizing deficient reviews.<n>It produces a final corpus of 6,634 papers, 24,657 real reviews, and 46,438 synthetic reviews.<n> deficient reviews demonstrate lower rating scores, higher self-reported confidence, reduced structural complexity, and a higher proportion of negative sentiment.
  arXiv  Detail & Related papers  (2025-10-18T15:45:26Z)
• When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review [34.067892820832405]
  This paper presents a systematic evaluation of large language models (LLMs) as academic reviewers.<n>Using a curated dataset of 1,441 papers from ICLR 2023 and NeurIPS 2022, we evaluate GPT-5-mini against human reviewers across ratings, strengths, and weaknesses.<n>Our findings show that LLMs consistently inflate ratings for weaker papers while aligning more closely with human judgments on stronger contributions.
  arXiv  Detail & Related papers  (2025-09-12T00:57:50Z)
• Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback [81.0031690510116]
  We present a structured approach for automated novelty evaluation that models expert reviewer behavior through three stages.<n>Our method is informed by a large scale analysis of human written novelty reviews.<n> Evaluated on 182 ICLR 2025 submissions, the approach achieves 86.5% alignment with human reasoning and 75.3% agreement on novelty conclusions.
  arXiv  Detail & Related papers  (2025-08-14T16:18:37Z)
• Can AI Solve the Peer Review Crisis? A Large Scale Cross Model Experiment of LLMs' Performance and Biases in Evaluating over 1000 Economics Papers [25.2441171957968]
  This study examines the potential of large language models (LLMs) to augment the academic peer review process by reliably evaluating the quality of economics research without introducing systematic bias.<n>We conduct one of the first large-scale experimental assessments of four LLMs across two complementary experiments.<n>We find that GPT, Gemma, and LLaMA assign significantly higher ratings to submissions from top male authors and elite institutions relative to the same papers presented anonymously.
  arXiv  Detail & Related papers  (2025-01-31T04:04:02Z)
• Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review [66.73247554182376]
  Large language models (LLMs) have led to their integration into peer review.<n>The unchecked adoption of LLMs poses significant risks to the integrity of the peer review system.<n>We show that manipulating 5% of the reviews could potentially cause 12% of the papers to lose their position in the top 30% rankings.
  arXiv  Detail & Related papers  (2024-12-02T16:55:03Z)
• Finding Blind Spots in Evaluator LLMs with Interpretable Checklists [23.381287828102995]
  We investigate the effectiveness of Large Language Models (LLMs) as evaluators for text generation tasks. We propose FBI, a novel framework designed to examine the proficiency of Evaluator LLMs in assessing four critical abilities.
  arXiv  Detail & Related papers  (2024-06-19T10:59:48Z)
• DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation [75.81096662788254]
  Large Language Models (LLMs) are scalable and economical evaluators.<n>The question of how reliable these evaluators are has emerged as a crucial research question.<n>We propose Decompose and Aggregate, which breaks down the evaluation process into different stages based on pedagogical practices.
  arXiv  Detail & Related papers  (2024-05-24T08:12:30Z)
• PRE: A Peer Review Based Large Language Model Evaluator [14.585292530642603]
  Existing paradigms rely on either human annotators or model-based evaluators to evaluate the performance of LLMs. We propose a novel framework that can automatically evaluate LLMs through a peer-review process.
  arXiv  Detail & Related papers  (2024-01-28T12:33:14Z)
• CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation [87.44350003888646]
  Eval-Instruct can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting. CritiqueLLM is empirically shown to outperform ChatGPT and all the open-source baselines.
  arXiv  Detail & Related papers  (2023-11-30T16:52:42Z)
• Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization [132.25202059478065]
  We benchmark large language models (LLMs) on instruction controllable text summarization. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs.
  arXiv  Detail & Related papers  (2023-11-15T18:25:26Z)
• L-Eval: Instituting Standardized Evaluation for Long Context Language Models [91.05820785008527]
  We propose L-Eval to institute a more standardized evaluation for long context language models (LCLMs) We build a new evaluation suite containing 20 sub-tasks, 508 long documents, and over 2,000 human-labeled query-response pairs. Results show that popular n-gram matching metrics generally can not correlate well with human judgment.
  arXiv  Detail & Related papers  (2023-07-20T17:59:41Z)
• G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment [64.01972723692587]
  We present G-Eval, a framework of using large language models with chain-of-thoughts (CoT) and a form-filling paradigm to assess the quality of NLG outputs. We show that G-Eval with GPT-4 as the backbone model achieves a Spearman correlation of 0.514 with human on summarization task, outperforming all previous methods by a large margin.
  arXiv  Detail & Related papers  (2023-03-29T12:46:54Z)

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.