# Defend: Automated Rebuttals for Peer Review with Minimal Author Guidance

arXiv: https://arxiv.org/abs/2603.27360 · HTML: https://mlsanity.com/paper/2603.27360/

## Key facts

- Cited by 4 papers in the map (data through 15 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 17 of 17)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications](https://mlsanity.com/paper/1804.09635/) (2018)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [Can We Automate Scientific Reviewing?](https://mlsanity.com/paper/2102.00176/) (2021)
- [NLPeer: A Unified Resource for the Computational Study of Peer Review](https://mlsanity.com/paper/2211.06651/) (2022)
- [Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions](https://mlsanity.com/paper/2406.05688/) (2024)
- [MReD: A Meta-Review Dataset for Structure-Controllable Text Generation](https://mlsanity.com/paper/2110.07474/) (2021)
- [Argument Mining for Understanding Peer Reviews](https://mlsanity.com/paper/1903.10104/) (2019)
- [DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions](https://mlsanity.com/paper/2110.08520/) (2021)
- [ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews](https://mlsanity.com/paper/2306.12587/) (2023)
- [MOPRD: A multidisciplinary open peer review dataset](https://mlsanity.com/paper/2212.04972/) (2022)
- [Ai2 Scholar QA: Organized Literature Synthesis with Attribution](https://mlsanity.com/paper/2504.10861/) (2025)
- [Re2: A Consistency-ensured Dataset for Full-stage Peer Review and Multi-turn Rebuttal Discussions](https://mlsanity.com/paper/2505.07920/) (2025)
- [Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach](https://mlsanity.com/paper/2211.06398/) (2022)
- [Exploring Jiu-Jitsu Argumentation for Writing Peer Review Rebuttals](https://mlsanity.com/paper/2311.03998/) (2023)
- [Insights from the ICLR Peer Review and Rebuttal Process](https://mlsanity.com/paper/2511.15462/) (2025)

## Built on by (most cited first, 4 of 4)

- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future](https://mlsanity.com/paper/2604.27924/) (2026)
- [PaperJury: Due-Process Review for Bounded LaTeX Revision](https://mlsanity.com/paper/2606.16322/) (2026)
- [Rebuttals Move Peer-Review Scores, but Initial-Review Structure Bounds the Movement](https://mlsanity.com/paper/2606.22166/) (2026)

## Abstract (arXiv)

Rebuttal generation is a critical component of the peer review process for scientific papers, enabling authors to clarify misunderstandings, correct factual inaccuracies, and guide reviewers toward a more accurate evaluation. We observe that Large Language Models (LLMs) often struggle to perform targeted refutation and maintain accurate factual grounding when used directly for rebuttal generation, highlighting the need for structured reasoning and author intervention. To address this, in the paper, we introduce DEFEND an LLM based tool designed to explicitly execute the underlying reasoning process of automated rebuttal generation, while keeping the author-in-the-loop. As opposed to writing the rebuttals from scratch, the author needs to only drive the reasoning process with minimal intervention, leading an efficient approach with minimal effort and less cognitive load. We compare DEFEND against three other paradigms: (i) Direct rebuttal generation using LLM (DRG), (ii) Segment-wise rebuttal generation using LLM (SWRG), and (iii) Sequential approach (SA) of segment-wise rebuttal generation without author intervention. To enable finegrained evaluation, we extend the ReviewCritique dataset, creating review segmentation, deficiency, error type annotations, rebuttal-action labels, and mapping to gold rebuttal segments. Experimental results and a user study demonstrate that directly using LLMs perform poorly in factual correctness and targeted refutation. Segment-wise generation and the automated sequential approach with author-in-the-loop, substantially improve factual correctness and strength of refutation.