Key points are not available for this paper at this time.
The de facto way of utilizing black-box large language models (LLMs) to perform various downstream tasks is prompting. However, obtaining suitable prompts for specific tasks is still a challenging problem. While existing LLM-based methods demonstrate promising performance in task-oriented dialogue (TOD) task, they often require manual adjustment in prompt selection, or focus solely on dialogue understanding or generation. To address these issues, we propose an adaptive prompt generation framework to fully unleash the potential of LLMs for the comprehensive TOD system. Firstly, we design a trainable slot generator (TSG) that can generate domain and slot information in the belief state, which serves as prior knowledge for subsequent prompt generation. Next, we propose an adaptive prompt generator (APG) that utilizes the prior knowledge to generate prompts for the LLM, deriving the belief state and system response of the dialogue for evaluation. Finally, we evaluate our framework on the MultiWOZ 2.0 dataset. Extensive experiments demonstrate that our method outperforms existing methods. Our code and data will be released.
Building similarity graph...
Analyzing shared references across papers
Loading...
Jun Gao
Chinese Academy of Medical Sciences & Peking Union Medical College
Liuyu Xiang
Beijing University of Posts and Telecommunications
Huijia Wu
Beijing Ditan Hospital
Beihang University
Beijing University of Posts and Telecommunications
Didi Chuxing (China)
Building similarity graph...
Analyzing shared references across papers
Loading...
Gao et al. (Sun,) studied this question.
synapsesocial.com/papers/6a12c40183732aa7db9e44fd — DOI: https://doi.org/10.18653/v1/2023.findings-emnlp.76
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: