@inproceedings{zhang-etal-2025-longcite,
    title = "{L}ong{C}ite: Enabling {LLM}s to Generate Fine-grained Citations in Long-Context {QA}",
    author = "Zhang, Jiajie  and
      Bai, Yushi  and
      Lv, Xin  and
      Gu, Wanjun  and
      Liu, Danqing  and
      Zou, Minhao  and
      Cao, Shulin  and
      Hou, Lei  and
      Dong, Yuxiao  and
      Feng, Ling  and
      Li, Juanzi",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/transition-to-people-yaml/2025.findings-acl.264/",
    doi = "10.18653/v1/2025.findings-acl.264",
    pages = "5098--5122",
    ISBN = "979-8-89176-256-5",
    abstract = "Though current long-context large language models (LLMs) have demonstrated impressive capacities in answering various questions based on extensive text, the lack of citations in their responses makes user verification difficult, leading to concerns about their trustworthiness due to the potential hallucinations. In this work, we aim to enable long-context LLMs to generate responses with fine-grained sentence-level citations on the fly, thereby improving their faithfulness and verifiability. We first introduce LongBench-Cite, an automated benchmark for assessing current LLMs' performance in long-context question answering with citations (LQAC), revealing considerable room for improvement. To this end, we propose CoF (Coarse to Fine), a novel pipeline that utilizes off-the-shelf LLMs to automatically construct long-context QA instances with precise sentence-level citations, and leverage this pipeline to construct LongCite-45k, a large-scale SFT dataset for LQAC. Finally, we train LongCite-8B and LongCite-9B using the constructed dataset, successfully enabling the generation of accurate responses and fine-grained citations in one pass. The evaluation results on LongBench-Cite show that our trained models achieve state-of-the-art citation quality, surpassing advanced proprietary models including GPT-4o. We also discover that SFT with citation information can further improve the correctness of model responses compared to standard long-context SFT."
}