Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review

TL;DR

This paper introduces a new dataset, framework, and evaluation suite for author-in-the-loop response generation in peer review, emphasizing author expertise, intent, and controllability.

Contribution

It presents the first large-scale dataset, a flexible response generation framework, and a comprehensive evaluation suite for integrating author signals into NLP responses.

Findings

Experiments show benefits of author input and evaluation-guided refinement.

Input specificity significantly impacts response quality.

Controllability and response quality exhibit trade-offs.

Abstract

Author response (rebuttal) writing is a critical stage of scientific peer review that demands substantial author effort. In practice, authors possess domain expertise, author-only information, and response strategies - concrete forms of author expertise and intent - and seek NLP assistance that integrates these signals into author response generation (ARG). Yet this author-in-the-loop paradigm lacks formal NLP formulation and systematic study: no dataset provides fine-grained author signals, existing ARG work lacks author inputs and controls, and no evaluation measures response reflection of author signals and effectiveness in addressing reviewer concerns. To fill these gaps, we introduce (i) Re3Align, the first large-scale dataset of aligned review-response-revision triplets, where revisions proxy author signals; (ii) REspGen, an author-in-the-loop ARG framework supporting flexible author input, multi-attribute control, and evaluation-guided refinement; and (iii) REspEval, a comprehensive evaluation suite with 20+ metrics spanning input utilization, controllability, response quality, and discourse. Experiments with SOTA LLMs demonstrate the benefits of author input and evaluation-guided refinement, the impact of input specificity on response quality, and controllability-quality trade-offs. We release our dataset, generation and evaluation tools.