Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.00492 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909374552735744 |
|---|---|
| author | Long, Do Xuan Yen, Duong Ngoc Luu, Anh Tuan Kawaguchi, Kenji Kan, Min-Yen Chen, Nancy F. |
| author_facet | Long, Do Xuan Yen, Duong Ngoc Luu, Anh Tuan Kawaguchi, Kenji Kan, Min-Yen Chen, Nancy F. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_00492 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models Long, Do Xuan Yen, Duong Ngoc Luu, Anh Tuan Kawaguchi, Kenji Kan, Min-Yen Chen, Nancy F. Computation and Language 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. |
| title | Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.00492 |