# ReviewGuard: Aligning LLM-Assisted Peer Review with Long-Term Scientific Impact

arXiv: https://arxiv.org/abs/2606.24892 · HTML: https://mlsanity.com/paper/2606.24892/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 57 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing](https://mlsanity.com/paper/2306.00622/) (2023)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning](https://mlsanity.com/paper/2511.22570/) (2025)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [Inconsistency in Conference Peer Review: Revisiting the 2014 NeurIPS Experiment](https://mlsanity.com/paper/2109.09774/) (2021)
- [Quantifying Long-Term Scientific Impact](https://mlsanity.com/paper/1306.3293/) (2013)
- [Prediction of citation dynamics of individual papers](https://mlsanity.com/paper/1910.00867/) (2019)
- [Analyzing the Machine Learning Conference Review Process](https://mlsanity.com/paper/2011.12919/) (2020)

## Built on by (most cited first, 2 of 2)

- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)
- [Learning Individual Scientific Taste with Privileged Hindsight Distillation](https://mlsanity.com/paper/2610.19719/) (2026)

## Abstract (arXiv)

Peer review is central to scientific quality control, yet it can undervalue papers that later achieve substantial citation impact. While frontier large language models have shown promise in automating aspects of peer review, they primarily mimic human reviewer preferences rather than predict long-term scientific value. We introduce ReviewGuard, a two-stage framework that aligns LLM-generated reviews with citation-based estimates of long-term scientific impact rather than contemporaneous reviewer judgments. On 20,861 AI/ML papers from OpenReview augmented with Semantic Scholar citation data, ReviewGuard achieves a Spearman correlation of rho = 0.776 with future citations on rejected-then-published papers, outperforming human reviewers (rho = 0.492) and a supervised Expert model (rho = 0.681). Under the same decision threshold, ReviewGuard flags 10.2% of high-impact rejected papers, compared with 1.8% for human reviewers, corresponding to a 5.6x improvement. Our results demonstrate that impact-aligned reinforcement learning can provide editors with a complementary signal for identifying high-potential work, without replacing human judgment.