# Can large language models provide useful feedback on research papers? A large-scale empirical analysis

arXiv: https://arxiv.org/abs/2310.01783 · HTML: https://mlsanity.com/paper/2310.01783/

## Key facts

- Cited by 200 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 69 references that are in the map.
- First posted on arXiv 3 Oct 2023.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [The Values Encoded in Machine Learning Research](https://mlsanity.com/paper/2106.15590/) (2021)
- [ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing](https://mlsanity.com/paper/2306.00622/) (2023)
- [Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research](https://mlsanity.com/paper/2112.01716/) (2021)
- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development](https://mlsanity.com/paper/2108.04308/) (2021)
- [GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study](https://mlsanity.com/paper/2307.05492/) (2023)
- [A Supervised Approach to Extractive Summarisation of Scientific Papers](https://mlsanity.com/paper/1706.03946/) (2017)
- [Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach](https://mlsanity.com/paper/2211.06398/) (2022)
- [REAL ML: Recognizing, Exploring, and Articulating Limitations of Machine Learning Research](https://mlsanity.com/paper/2205.08363/) (2022)

## Built on by (most cited first, 30 of 200)

- [FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts](https://mlsanity.com/paper/2311.05608/) (2023)
- [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [Empowering Biomedical Discovery with AI Agents](https://mlsanity.com/paper/2404.02831/) (2024)
- [MARG: Multi-Agent Review Generation for Scientific Papers](https://mlsanity.com/paper/2401.04259/) (2024)
- [A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery](https://mlsanity.com/paper/2406.10833/) (2024)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [BLADE: Benchmarking Language Model Agents for Data-Driven Science](https://mlsanity.com/paper/2408.09667/) (2024)
- [AgentRxiv: Towards Collaborative Autonomous Research](https://mlsanity.com/paper/2503.18102/) (2025)
- [Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning](https://mlsanity.com/paper/2504.17192/) (2025)
- [OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews](https://mlsanity.com/paper/2412.11948/) (2024)
- [LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing](https://mlsanity.com/paper/2406.16253/) (2024)
- [Large language models for automated scholarly paper review: A survey](https://mlsanity.com/paper/2501.10326/) (2025)
- [Experiential Co-Learning of Software-Developing Agents](https://mlsanity.com/paper/2312.17025/) (2023)
- [Autonomous LLM-driven research from data to human-verifiable research papers](https://mlsanity.com/paper/2404.17605/) (2024)
- [Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025](https://mlsanity.com/paper/2504.09737/) (2025)
- [Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions](https://mlsanity.com/paper/2406.05688/) (2024)
- [AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviews](https://mlsanity.com/paper/2408.10365/) (2024)
- [Automated Hypothesis Validation with Agentic Sequential Falsifications](https://mlsanity.com/paper/2502.09858/) (2025)
- [IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback](https://mlsanity.com/paper/2410.04025/) (2024)
- [Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation](https://mlsanity.com/paper/2502.05151/) (2025)
- [ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code](https://mlsanity.com/paper/2506.02314/) (2025)
- [Large Language Models for Education: A Survey](https://mlsanity.com/paper/2405.13001/) (2024)
- [Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards](https://mlsanity.com/paper/2505.04966/) (2025)
- [Automated Focused Feedback Generation for Scientific Writing Assistance](https://mlsanity.com/paper/2405.20477/) (2024)
- [Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis](https://mlsanity.com/paper/2407.12857/) (2024)
- [ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews](https://mlsanity.com/paper/2503.08506/) (2025)
- [Scientific production in the era of Large Language Models](https://mlsanity.com/paper/2601.13187/) (2026)
- [TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review](https://mlsanity.com/paper/2506.07642/) (2025)

## Abstract (arXiv)

Expert feedback lays the foundation of rigorous research. However, the rapid growth of scholarly production and intricate knowledge specialization challenge the conventional scientific feedback mechanisms. High-quality peer reviews are increasingly difficult to obtain. Researchers who are more junior or from under-resourced settings have especially hard times getting timely feedback. With the breakthrough of large language models (LLM) such as GPT-4, there is growing interest in using LLMs to generate scientific feedback on research manuscripts. However, the utility of LLM-generated feedback has not been systematically studied. To address this gap, we created an automated pipeline using GPT-4 to provide comments on the full PDFs of scientific papers. We evaluated the quality of GPT-4's feedback through two large-scale studies. We first quantitatively compared GPT-4's generated feedback with human peer reviewer feedback in 15 Nature family journals (3,096 papers in total) and the ICLR machine learning conference (1,709 papers). The overlap in the points raised by GPT-4 and by human reviewers (average overlap 30.85% for Nature journals, 39.23% for ICLR) is comparable to the overlap between two human reviewers (average overlap 28.58% for Nature journals, 35.25% for ICLR). The overlap between GPT-4 and human reviewers is larger for the weaker papers. We then conducted a prospective user study with 308 researchers from 110 US institutions in the field of AI and computational biology to understand how researchers perceive feedback generated by our GPT-4 system on their own papers. Overall, more than half (57.4%) of the users found GPT-4 generated feedback helpful/very helpful and 82.4% found it more beneficial than feedback from at least some human reviewers. While our findings show that LLM-generated feedback can help researchers, we also identify several limitations.