多专家提示提高了大型语言模型的可靠性、安全性和实用性。

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

November 1, 2024

作者: Do Xuan Long, Duong Ngoc Yen, Anh Tuan Luu, Kenji Kawaguchi, Min-Yen Kan, Nancy F. Chen

cs.AI

摘要

我们提出了多专家提示（Multi-expert Prompting），这是对ExpertPrompting（Xu等，2023年）的一项新颖增强，旨在改善大型语言模型（LLM）的生成。具体而言，它通过模拟多个专家，汇总他们的回应，并从个体和汇总回应中选择最佳回应，引导LLM完成输入指令。这一过程通过我们从名义小组技术（Ven和Delbecq，1974年）中精心设计的七个子任务在一条思维链中执行，该技术是一个成熟的决策框架。我们的评估表明，多专家提示在增强响应的真实性、事实性、信息量和实用性方面明显优于ExpertPrompting和可比较的基线，同时减少了毒性和伤害性。它通过超越ChatGPT的最佳基线，使真实性达到了最先进水平，超出了8.69%。多专家提示高效、可解释，并且高度适应各种场景，消除了手动提示构建的需要。

English

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.