Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models

TL;DR

Multi-expert Prompting enhances large language model responses by simulating multiple experts, aggregating their outputs, and selecting the best, leading to improved truthfulness, safety, and usefulness without manual prompt tuning.

Contribution

It introduces a novel multi-expert prompting method that outperforms existing techniques in reliability, safety, and informativeness of LLM outputs, using a decision-making framework.

Findings

Outperforms ExpertPrompting and baselines in truthfulness and factuality.

Reduces toxicity and hurtfulness in responses.

Achieves 8.69% higher truthfulness with ChatGPT.

Abstract

We present Multi-expert Prompting, a novel enhancement of ExpertPrompting (Xu et al., 2023), designed to improve the large language model (LLM) generation. Specifically, it guides an LLM to fulfill an input instruction by simulating multiple experts, aggregating their responses, and selecting the best among individual and aggregated responses. This process is performed in a single chain of thoughts through our seven carefully designed subtasks derived from the Nominal Group Technique (Ven and Delbecq, 1974), a well-established decision-making framework. Our evaluations demonstrate that Multi-expert Prompting significantly outperforms ExpertPrompting and comparable baselines in enhancing the truthfulness, factuality, informativeness, and usefulness of responses while reducing toxicity and hurtfulness. It further achieves state-of-the-art truthfulness by outperforming the best baseline by 8.69% with ChatGPT. Multi-expert Prompting is efficient, explainable, and highly adaptable to diverse scenarios, eliminating the need for manual prompt construction.