Faithful Question Answering with Monte-Carlo Planning
Ruixin Hong, Hongming Zhang, Hong Zhao, Dong Yu, Changshui Zhang
Abstract
Although large language models demonstrate remarkable question-answering performances, revealing the intermediate reasoning steps that the models faithfully follow remains challenging. In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps. The reasoning steps are organized as a structured entailment tree, which shows how premises are used to produce intermediate conclusions that can prove the correctness of the answer. We formulate the task as a discrete decision-making problem and solve it through the interaction of a reasoning environment and a controller. The environment is modular and contains several basic task-oriented modules, while the controller proposes actions to assemble the modules. Since the search space could be large, we introduce a Monte-Carlo planning algorithm to do a look-ahead search and select actions that will eventually lead to high-quality steps. FAME achieves advanced performance on the standard benchmark. It can produce valid and faithful reasoning steps compared with large language models with a much smaller model size.- Anthology ID:
- 2023.acl-long.218
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3944–3965
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.218
- DOI:
- Cite (ACL):
- Ruixin Hong, Hongming Zhang, Hong Zhao, Dong Yu, and Changshui Zhang. 2023. Faithful Question Answering with Monte-Carlo Planning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3944–3965, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Faithful Question Answering with Monte-Carlo Planning (Hong et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2023.acl-long.218.pdf