# Reviewer2: Optimizing Review Generation Through Prompt Generation

arXiv: https://arxiv.org/abs/2402.10886 · HTML: https://mlsanity.com/paper/2402.10886/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2024.

## Built on by (most cited first, 7 of 7)

- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [DIAGPaper: Diagnosing Valid and Specific Weaknesses in Scientific Papers via Multi-Agent Reasoning](https://mlsanity.com/paper/2601.07611/) (2026)
- [From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent](https://mlsanity.com/paper/2606.13349/) (2026)
- [PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers](https://mlsanity.com/paper/2605.26730/) (2026)
- [CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers](https://mlsanity.com/paper/2605.07905/) (2026)
- [Verify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents](https://mlsanity.com/paper/2610.08993/) (2026)
- [Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review](https://mlsanity.com/paper/2610.11087/) (2026)

## Abstract (arXiv)

Recent developments in LLMs offer new opportunities for assisting authors in improving their work. In this paper, we envision a use case where authors can receive LLM-generated reviews that uncover weak points in the current draft. While initial methods for automated review generation already exist, these methods tend to produce reviews that lack detail, and they do not cover the range of opinions that human reviewers produce. To address this shortcoming, we propose an efficient two-stage review generation framework called Reviewer2. Unlike prior work, this approach explicitly models the distribution of possible aspects that the review may address. We show that this leads to more detailed reviews that better cover the range of aspects that human reviewers identify in the draft. As part of the research, we generate a large-scale review dataset of 27k papers and 99k reviews that we annotate with aspect prompts, which we make available as a resource for future research.