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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Nuo, HuiKai, Andre Lin, Wu, Jiaying, Hou, Junyi, Zhang, Zining, Wang, Qian, Wang, Xidong, He, Bingsheng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913056755286016
author Chen, Nuo
HuiKai, Andre Lin
Wu, Jiaying
Hou, Junyi
Zhang, Zining
Wang, Qian
Wang, Xidong
He, Bingsheng
author_facet Chen, Nuo
HuiKai, Andre Lin
Wu, Jiaying
Hou, Junyi
Zhang, Zining
Wang, Qian
Wang, Xidong
He, Bingsheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11336
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration
Chen, Nuo
HuiKai, Andre Lin
Wu, Jiaying
Hou, Junyi
Zhang, Zining
Wang, Qian
Wang, Xidong
He, Bingsheng
Computation and Language
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.
title XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration
topic Computation and Language
url https://arxiv.org/abs/2505.11336