XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration

TL;DR

XtraGPT is an open-source, context-aware LLM framework designed for high-quality academic paper revision through human-AI collaboration, addressing the limitations of existing scientific writing tools.

Contribution

It introduces a novel human-AI collaboration framework with criteria-guided intent alignment and context modeling, and provides a fine-tuned LLM suite for academic revision.

Findings

XtraGPT outperforms baseline models in scientific draft improvement.

Automated and human evaluations confirm XtraGPT's effectiveness.

The dataset of 7,000 papers and 140,000 instruction-response pairs supports realistic scientific revisions.

Abstract

Despite the growing adoption of large language models (LLMs) in academic workflows, their capabilities remain limited in supporting high-quality scientific writing. Most existing systems are designed for general-purpose scientific text generation and fail to meet the sophisticated demands of research communication beyond surface-level polishing, for example, maintaining conceptual coherence across sections. Furthermore, academic writing is inherently iterative and revision-driven, a process that is not well supported by direct prompting-based paradigms. To address these scenarios, we propose a human-AI collaboration framework for academic paper revision, centered on criteria-guided intent alignment and context-aware modeling. To validate the framework, we curate a dataset of 7,000 research papers from top-tier venues, annotated with 140,000 instruction--response pairs that reflect realistic, section-level scientific revisions. We instantiate the framework in XtraGPT, the first suite of open-source LLMs (1.5B to 14B parameters) specifically fine-tuned for context-aware academic paper revision. Extensive experiments show that XtraGPT significantly outperforms same-scale baselines and rivals the quality of proprietary counterparts. Both automated preference assessments and human evaluations confirm the effectiveness of XtraGPT in improving scientific drafts. Our code and models are available at https://github.com/Xtra-Computing/XtraGPT and https://huggingface.co/collections/Xtra-Computing/xtragpt.