@inproceedings{chen-etal-2025-llms,
    title = "Can {LLM}s Recognize Their Own Analogical Hallucinations? Evaluating Uncertainty Estimation for Analogical Reasoning",
    author = "Chen, Zheng  and
      Feng, Zhaoxin  and
      Ma, Jianfei  and
      Xu, Jiexi  and
      Li, Bo",
    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-1.8/",
    pages = "84--93",
    ISBN = "979-8-89176-283-1",
    abstract = "Large language models (LLMs) often demonstrate strong performance by leveraging implicit knowledge acquired during pretraining. Analogical reasoning, which solves new problems by referencing similar known examples, offers a structured way to utilize this knowledge, but can also lead to subtle factual errors and hallucinations. In this work, we investigate whether LLMs can recognize the reliability of their own analogical outputs using black-box uncertainty estimation (UE). We evaluate six UE metrics across two reasoning-intensive tasks: mathematical problem solving (GSM8K) and code generation (Codeforces). Our results show that Kernel Language Entropy (KLE) and Lexical Similarity (LexSim) are the most robust indicators of correctness. Moreover, while analogical prompting increases model confidence over direct prompting, most uncertainty arises during the analogy transfer step. These findings highlight the limitations of analogical knowledge transfer in LLMs and demonstrate the potential of UE methods for detecting hallucinated reasoning in black-box settings."
}