2023年11月1日 · Experimental results demonstrate that PPDPP consistently and substantially outperforms existing approaches on three different proactive dialogue applications, including …

2024年9月15日 · 提出了一种新的对话策略规划范式，名为PPDPP（Plug-and-play Policy Dialogue Planner），用于为大语言模型（LLM）驱动的对话代理制定策略。PPDPP通过插拔 …

Yang Deng, PhD student in CUHK. dengyang17 has 20 repositories available. Follow their code on GitHub.

2024年1月12日 · (1) Implement and oversee the use of PPDPP pay authorities. (2) Serve as the AMO in all determinations of market pay amounts for civilian physicians, podiatrists, and …

PPDPP (Table 25). The proposed PPDPP, similar to ProCoT, can employ effective negotiation strategies to reach a much better deal. Furthermore, when the seller expresses his/her …

2023年11月1日 · In this work, we introduce a new dialogue policy planning paradigm to strategize LLMs for proactive dialogue problems with a tunable language model plug-in as a plug-and …

Contribute to dengyang17/PPDPP development by creating an account on GitHub. We read every piece of feedback, and take your input very seriously.

本文提出了一种用于策划大型语言模型（llms）主动对话问题的新型对话策略规划范式，名为ppdpp，通过可调节的语言模型插件来提高llms的主动性。 实验证明，在谈判、情感支持和辅 …

为此，我们提出了双重加工对话规划（DPDP）框架，这是一种将两种互补规划系统相结合的新方法：神经策略语言模型（系统1）用于快速、直觉地应对熟悉的情境，而基于MCTS的规划 …

2024年1月16日 · Experimental results demonstrate that PPDPP consistently and substantially outperforms existing approaches on three different proactive dialogue applications, including …