@inproceedings{chen-etal-2025-teaching,
    title = "Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals",
    author = "Chen, Lida  and
      Liang, Zujie  and
      Wang, Xintao  and
      Liang, Jiaqing  and
      Xiao, Yanghua  and
      Wei, Feng  and
      Chen, Jinglei  and
      Hao, Zhenghong  and
      Han, Bing  and
      Wang, Wei",
    editor = "Zhang, Yuji  and
      Chen, Canyu  and
      Li, Sha  and
      Geva, Mor  and
      Han, Chi  and
      Wang, Xiaozhi  and
      Feng, Shangbin  and
      Gao, Silin  and
      Augenstein, Isabelle  and
      Bansal, Mohit  and
      Li, Manling  and
      Ji, Heng",
    booktitle = "Proceedings of the 3rd Workshop on Towards Knowledgeable Foundation Models (KnowFM)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.knowfm-1.3/",
    pages = "26--39",
    ISBN = "979-8-89176-283-1",
    abstract = "Large language models (LLMs) have achieved great success, but their occasional content fabrication, or hallucination, limits their practical application. Hallucination arises because LLMs struggle to admit ignorance due to inadequate training on knowledge boundaries. We call it a limitation of LLMs that they can not accurately express their knowledge boundary, answering questions they know while admitting ignorance to questions they do not know. In this paper, we aim to teach LLMs to recognize and express their knowledge boundary, so they can reduce hallucinations caused by fabricating when they do not know. We propose CoKE, which first probes LLMs' knowledge boundary via internal confidence given a set of questions, and then leverages the probing results to elicit the expression of the knowledge boundary. Extensive experiments show CoKE helps LLMs express knowledge boundaries, answering known questions while declining unknown ones, significantly improving in-domain and out-of-domain performance."
}