Academic writing with learned citation retrieval

ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations

Wang, Yubo, Ma, Xueguang, Nie, Ping, Zeng, Huaye, Lyu, Zhiheng, Zhang, Yuxuan, Schneider, Benjamin, Lu, Yi, Yue, Xiang, Chen, Wenhu

Paper / source record · 2025-04-01

Project Paper Code Dataset Model Demo Video overview Evidence worksheet

Research question and approach

Academic writing requires coherent text and relevant references. Generating a plausible citation string does not establish that a paper exists or supports a claim. ScholarCopilot combines scholarly writing with learned retrieval of references.

When this work is relevant

Cite this work when discussing joint academic text generation and citation retrieval, or when using its released writing model and retrieval setup.

Author-written abstract

Academic writing requires both coherent text generation and precise citation of relevant literature. Although recent Retrieval-Augmented Generation (RAG) systems have significantly improved factual accuracy in general-purpose text generation, their ability to support professional academic writing remains limited. In this work, we introduce ScholarCopilot, a unified framework designed to enhance existing large language models for generating professional academic articles with accurate and contextually relevant citations. ScholarCopilot dynamically determines when to retrieve scholarly references by generating a retrieval token [RET], which is then used to query a citation database. The retrieved references are fed into the model to augment the generation process. We jointly optimize both the generation and citation tasks within a single framework to improve efficiency. Our model is built upon Qwen-2.5-7B and trained on 500K papers from arXiv. It achieves a top-1 retrieval accuracy of 40.1% on our evaluation dataset, outperforming baselines such as E5-Mistral-7B-Instruct (15.0%) and BM25 (9.8%). On a dataset of 1,000 academic writing samples, ScholarCopilot scores 16.2/25 in generation quality -- measured across relevance, coherence, academic rigor, completeness, and innovation -- significantly surpassing all existing models, including much larger ones like the Retrieval-Augmented Qwen2.5-72B-Instruct. Human studies further demonstrate that ScholarCopilot, despite being a 7B model, significantly outperforms ChatGPT, achieving 100% preference in citation quality and over 70% in overall usefulness.

Abstract source: https://arxiv.org/abs/2504.00824. Checked 2026-09-14. Bibliographic metadata uses the linked paper record or author-maintained catalog. Results, limitations and experimental settings remain defined by the original source.

Citation

BibTeX · CITATION.cff

BibTeX is preserved from the author-maintained citation repository. The CFF uses the source metadata shown on this page. Version titles or author lists can differ; choose the version you used.

@article{wang2025scholarcopilot,
  title={Scholarcopilot: Training large language models for academic writing with accurate citations},
  author={Wang, Yubo and Ma, Xueguang and Nie, Ping and Zeng, Huaye and Lyu, Zhiheng and Zhang, Yuxuan and Schneider, Benjamin and Lu, Yi and Yue, Xiang and Chen, Wenhu},
  journal={arXiv preprint arXiv:2504.00824},
  year={2025}
}