@inproceedings{shen-etal-2025-transparentize,
    title = "Transparentize the Internal and External Knowledge Utilization in {LLM}s with Trustworthy Citation",
    author = "Shen, Jiajun  and
      Zhou, Tong  and
      Chen, Yubo  and
      Qiu, Delai  and
      Liu, Shengping  and
      Liu, Kang  and
      Zhao, Jun",
    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/ingestion-acl-25/2025.findings-acl.919/",
    pages = "17858--17877",
    ISBN = "979-8-89176-256-5",
    abstract = "While hallucinations of large language models could be alleviated through retrieval-augmented generation and citation generation, how the model utilizes internal knowledge is still opaque, and the trustworthiness of its generated answers remains questionable. In this work, we introduce Context-Prior Augmented Citation Generation task, requiring models to generate citations considering both external and internal knowledge while providing trustworthy references, with 5 evaluation metrics focusing on 3 aspects: answer helpfulness, citation faithfulness, and trustworthiness. We introduce RAEL, the paradigm for our task, and also design INTRALIGN, an integrated method containing customary data generation and an alignment algorithm. Our experimental results show that our method achieves a better cross-scenario performance with regard to other baselines. Our extended experiments further reveal that retrieval quality, question types, and model knowledge have considerable influence on the trustworthiness in citation generation."
}