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

Do Long, Duong Yen, Anh Tuan Luu, Kenji Kawaguchi, Min-Yen Kan, Nancy Chen


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.
Anthology ID:
2024.emnlp-main.1135
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
20370–20401
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1135
DOI:
Bibkey:
Cite (ACL):
Do Long, Duong Yen, Anh Tuan Luu, Kenji Kawaguchi, Min-Yen Kan, and Nancy Chen. 2024. Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 20370–20401, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models (Long et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1135.pdf