Abstract
Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such as A* search and Monte Carlo Tree Search (MCTS). However, this training often require abundant annotated data, which creates challenges when faced with noisy annotations or low-resource settings. We introduce GDP-Zero, an approach using Open-Loop MCTS to perform goal-oriented dialogue policy planning without any model training. GDP-Zero prompts a large language model to act as a policy prior, value function, user simulator, and system model during the tree search. We evaluate GDP-Zero on the goal-oriented task PersuasionForGood, and find that its responses are preferred over ChatGPT up to 59.32% of the time, and are rated more persuasive than ChatGPT during interactive evaluations.- Anthology ID:
- 2023.emnlp-main.439
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7101–7125
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.439
- DOI:
- 10.18653/v1/2023.emnlp-main.439
- Cite (ACL):
- Xiao Yu, Maximillian Chen, and Zhou Yu. 2023. Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7101–7125, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning (Yu et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.439.pdf