Mitigating Hallucination in Large Language Models with Explanatory Prompting

A growing concern with the use of Large Language Models (LLMs) is the presenceof hallucinated outputs. For tasks that require complex reasoning, hallucinationsmake LLMs unreliable and thus unsafe to deploy in a range of applications fromhealthcare to education. To combat this issue, we propose explanatory prompting,a methodology that gives an informal logical description of an algorithm neededto solve all instances of a given problem. To illustrate the use of explanatoryprompting, we consider a Graph Connectivity problem on directed acyclic graphs.We evaluate our approach by experiments on the Flight Connectivity dataset, aninstance of a Graph Connectivity problem (Zhang et al., 2023a). Our experimentsdemonstrate a decrease in hallucination rate from 44.8% in prior work to 1.8%using explanatory prompting. At the same time, we confirm that calibrated LLMsare bound to hallucinate by experimentally verifying a theoretical lower bound forhallucination (Kalai and Vempala, 2024).