Conformal Prediction with Large Language Models for Multi-Choice Question Answering
This work addresses the need for robust uncertainty quantification in high-stakes scenarios to enable safer deployment of large language models, though it is incremental as it applies an existing technique to a specific task.
The paper tackled the problem of uncertainty quantification for large language models in multiple-choice question answering by applying conformal prediction, finding that uncertainty estimates are tightly correlated with prediction accuracy, which can aid in selective classification and filtering low-quality predictions.
As large language models continue to be widely developed, robust uncertainty quantification techniques will become crucial for their safe deployment in high-stakes scenarios. In this work, we explore how conformal prediction can be used to provide uncertainty quantification in language models for the specific task of multiple-choice question-answering. We find that the uncertainty estimates from conformal prediction are tightly correlated with prediction accuracy. This observation can be useful for downstream applications such as selective classification and filtering out low-quality predictions. We also investigate the exchangeability assumption required by conformal prediction to out-of-subject questions, which may be a more realistic scenario for many practical applications. Our work contributes towards more trustworthy and reliable usage of large language models in safety-critical situations, where robust guarantees of error rate are required.