# Generating Edit-Inducing Questions for AI Research Manuscripts

arXiv: https://arxiv.org/abs/2609.36617 · HTML: https://mlsanity.com/paper/2609.36617/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications](https://mlsanity.com/paper/1804.09635/) (2018)
- [ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing](https://mlsanity.com/paper/2306.00622/) (2023)
- [MARG: Multi-Agent Review Generation for Scientific Papers](https://mlsanity.com/paper/2401.04259/) (2024)
- [ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis](https://mlsanity.com/paper/2010.06119/) (2020)
- [Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards](https://mlsanity.com/paper/2505.04966/) (2025)
- [PeerQA: A Scientific Question Answering Dataset from Peer Reviews](https://mlsanity.com/paper/2502.13668/) (2025)
- [QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing](https://mlsanity.com/paper/2310.14520/) (2023)
- [A Novice-Reviewer Experiment to Address Scarcity of Qualified Reviewers in Large Conferences](https://mlsanity.com/paper/2011.15050/) (2020)

## Abstract (arXiv)

We study the ability of LLMs to generate edit-inducing questions whose answer will improve a paper draft. On a dataset of paired submission and camera-ready papers from ICLR and NeurIPS, we compare the helpfulness of questions from GPT models with or without full paper context to that of human reviewers. GPT produces more edit-inducing questions and its questions are associated with more extensive edits and cover a broader range of edited content compared to questions from reviewers. However, a much smaller percentage of the GPT questions are edit-inducing. Our analyses confirm that automated questions can be beneficial to authors and highlight an example task where proper attending to long context deteriorates reasoning model ability to produce helpful output.