TRAC: Trustworthy Retrieval Augmented Chatbot

Shuo Li, Sangdon Park, Insup Lee, Osbert Bastani

Keywords: Trustworthy AI; Question Answering; Conformal Prediction; Knowledge Retrieval

TL;DR: We provide statistical guarantees for retrieval augmented question answering systems.

Abstract: Although neural conversational AIs have demonstrated fantastic performance, they often generate incorrect information, or \textit{hallucinations}. Retrieval augmented generation has emerged as a promising solution to reduce these hallucinations. However, these techniques still cannot guarantee correctness. Focusing on question answering, we propose a framework that can provide statistical guarantees for the retrieval augmented question answering system by combining conformal prediction and global testing. In addition, we use Bayesian optimization to choose hyperparameters of the global test to maximize the performance of the system. Our empirical results on the Natural Questions dataset demonstrate that our method can provide the desired coverage guarantee while minimizing the average prediction set size.

Submission Number: 7