LogiCoT: Logical Chain-of-Thought Instruction Tuning

Hanmeng Liu, Zhiyang Teng, Leyang Cui, Chaoli Zhang, Qiji Zhou, Yue Zhang


Abstract
Generative Pre-trained Transformer 4 (GPT-4) demonstrates impressive chain-of-thought reasoning ability. Recent work on self-instruction tuning, such as Alpaca, has focused on enhancing the general proficiency of models. These instructions enable the model to achieve performance comparable to GPT-3.5 on general tasks like open-domain text generation and paraphrasing. However, they fall short of helping the model handle complex reasoning tasks. To bridge the gap, this paper presents LogiCoT, a new instruction-tuning dataset for Logical Chain-of-Thought reasoning with GPT-4. We elaborate on the process of harvesting instructions for prompting GPT-4 to generate chain-of-thought rationales. LogiCoT serves as an instruction set for teaching models of logical reasoning and elicits general reasoning skills.
Anthology ID:
2023.findings-emnlp.191
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2908–2921
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.191
DOI:
10.18653/v1/2023.findings-emnlp.191
Bibkey:
Cite (ACL):
Hanmeng Liu, Zhiyang Teng, Leyang Cui, Chaoli Zhang, Qiji Zhou, and Yue Zhang. 2023. LogiCoT: Logical Chain-of-Thought Instruction Tuning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2908–2921, Singapore. Association for Computational Linguistics.
Cite (Informal):
LogiCoT: Logical Chain-of-Thought Instruction Tuning (Liu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.findings-emnlp.191.pdf