Large language models (LLMs) are increasingly deployed in real-world question-answering (QA) applications. However, LLMs have been proven to generate hallucinations and nonfactual information, undermining their trustworthiness in high-stakes medical tasks. Conformal prediction (CP) is well-known to be model-agnostic and distribution-free, which creates statistically rigorous prediction sets in classification tasks. In this work, we for the first time adapt the CP framework to medical multiple-choice question-answering (MCQA) tasks, by correlating the nonconformity score with the frequency score of correct options grounded in self-consistency theory, assuming no access to internal model information. Considering that the adapted CP framework can only control the (mis)coverage rate, we employ a risk control framework, which can manage task-specific metrics by devising a monotonically decreasing loss function. We evaluate our framework on 3 popular medical MCQA datasets utilizing 4 ``off-the-shelf'' LLMs. Empirical results demonstrate that we achieve user-specified average (or marginal) error rates on the test set. Furthermore, we observe that the average prediction set size (APSS) on the test set decreases as the risk level increases, which concludes a promising evaluation metric for the uncertainty of LLMs.

翻译：暂无翻译