LAMBADA: Backward Chaining for Automated Reasoning in Natural Language
Mehran Kazemi, Najoung Kim, Deepti Bhatia, Xin Xu, Deepak Ramachandran
Abstract
Remarkable progress has been made on automated reasoning with natural text, by using Large Language Models (LLMs) and methods such as Chain-of-Thought prompting and Selection-Inference. These techniques search for proofs in the forward direction from axioms to the conclusion, which suffers from a combinatorial explosion of the search space, and thus high failure rates for problems requiring longer chains of reasoning. The classical automated reasoning literature has shown that reasoning in the backward direction (i.e. from intended conclusion to supporting axioms) is significantly more efficient at proof-finding. Importing this intuition into the LM setting, we develop a Backward Chaining algorithm, called LAMBADA, that decomposes reasoning into four sub-modules, that are simply implemented by few-shot prompted LLM inference. We show that LAMBADA achieves sizable accuracy boosts over state-of-the-art forward reasoning methods on two challenging logical reasoning datasets, particularly when deep and accurate proof chains are required.- Anthology ID:
- 2023.acl-long.361
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6547–6568
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.361
- DOI:
- 10.18653/v1/2023.acl-long.361
- Cite (ACL):
- Mehran Kazemi, Najoung Kim, Deepti Bhatia, Xin Xu, and Deepak Ramachandran. 2023. LAMBADA: Backward Chaining for Automated Reasoning in Natural Language. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6547–6568, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- LAMBADA: Backward Chaining for Automated Reasoning in Natural Language (Kazemi et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.acl-long.361.pdf