ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929725423747072 |
|---|---|
| author | Li, Zhigen Peng, Jianxiang Wang, Yanmeng Cao, Yong Shen, Tianhao Zhang, Minghui Su, Linxi Wu, Shang Wu, Yihang Wang, Yuqian Wang, Ye Hu, Wei Li, Jianfeng Wang, Shaojun Xiao, Jing Xiong, Deyi |
| author_facet | Li, Zhigen Peng, Jianxiang Wang, Yanmeng Cao, Yong Shen, Tianhao Zhang, Minghui Su, Linxi Wu, Shang Wu, Yihang Wang, Yuqian Wang, Ye Hu, Wei Li, Jianfeng Wang, Shaojun Xiao, Jing Xiong, Deyi |
| contents | Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their lack of controllability remains a key challenge, often leading to unfocused conversations or task failure. To address this, we introduce Standard Operating Procedure (SOP) to regulate dialogue flow. Specifically, we propose ChatSOP, a novel SOP-guided Monte Carlo Tree Search (MCTS) planning framework designed to enhance the controllability of LLM-driven dialogue agents. To enable this, we curate a dataset comprising SOP-annotated multi-scenario dialogues, generated using a semi-automated role-playing system with GPT-4o and validated through strict manual quality control. Additionally, we propose a novel method that integrates Chain of Thought reasoning with supervised fine-tuning for SOP prediction and utilizes SOP-guided Monte Carlo Tree Search for optimal action planning during dialogues. Experimental results demonstrate the effectiveness of our method, such as achieving a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also showing notable gains for open-source models. Dataset and codes are publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03884 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents Li, Zhigen Peng, Jianxiang Wang, Yanmeng Cao, Yong Shen, Tianhao Zhang, Minghui Su, Linxi Wu, Shang Wu, Yihang Wang, Yuqian Wang, Ye Hu, Wei Li, Jianfeng Wang, Shaojun Xiao, Jing Xiong, Deyi Computation and Language Artificial Intelligence Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their lack of controllability remains a key challenge, often leading to unfocused conversations or task failure. To address this, we introduce Standard Operating Procedure (SOP) to regulate dialogue flow. Specifically, we propose ChatSOP, a novel SOP-guided Monte Carlo Tree Search (MCTS) planning framework designed to enhance the controllability of LLM-driven dialogue agents. To enable this, we curate a dataset comprising SOP-annotated multi-scenario dialogues, generated using a semi-automated role-playing system with GPT-4o and validated through strict manual quality control. Additionally, we propose a novel method that integrates Chain of Thought reasoning with supervised fine-tuning for SOP prediction and utilizes SOP-guided Monte Carlo Tree Search for optimal action planning during dialogues. Experimental results demonstrate the effectiveness of our method, such as achieving a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also showing notable gains for open-source models. Dataset and codes are publicly available. |
| title | ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.03884 |