Can LLMs Recognize Their Own Analogical Hallucinations? Evaluating Uncertainty Estimation for Analogical Reasoning

Zheng CHEN, Zhaoxin Feng, Jianfei Ma, Jiexi Xu, Bo Li

Keywords: Large Language Models, Analogical Reasoning, Uncertainty Estimation, Hallucination Detection, Knowledge Utilization, Black-box Evaluation, Trustworthy AI, Factual Consistency

TL;DR: We assess if LLMs can self-identify failures in analogical reasoning using black-box uncertainty metrics. Our results reveal that transfer is the most hallucination-prone stage.

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.

Archival Status: Archival (included in proceedings)

Submission Number: 51