Abstract
Large language models (LLMs) often struggle with complex logical reasoning due to logical inconsistencies and the inherent difficulty ofsuch reasoning. We use Lean, a theorem proving framework, to address these challenges. By formalizing logical reasoning problems intotheorems within Lean, we can solve them by proving or disproving the corresponding theorems. This method reduces the risk of logical inconsistencies with the help of Lean’s symbolic solver. It also enhances our ability to treat complex reasoning tasks using Lean’s extensive library of theorem proofs. Our method achieves state-of-the-art performance on the FOLIO dataset and achieves performance near this level on ProofWriter. Notably, these results were accomplished by fine-tuning on fewer than 100 in-domain samples for each dataset- Anthology ID:
- 2024.naacl-long.416
- Volume:
- Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Kevin Duh, Helena Gomez, Steven Bethard
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7497–7510
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2024.naacl-long.416/
- DOI:
- 10.18653/v1/2024.naacl-long.416
- Cite (ACL):
- Dongwei Jiang, Marcio Fonseca, and Shay Cohen. 2024. LeanReasoner: Boosting Complex Logical Reasoning with Lean. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7497–7510, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- LeanReasoner: Boosting Complex Logical Reasoning with Lean (Jiang et al., NAACL 2024)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2024.naacl-long.416.pdf