ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models

Zhipeng Chen, Kun Zhou, Beichen Zhang, Zheng Gong, Xin Zhao, Ji-Rong Wen


Abstract
Although large language models (LLMs) have achieved excellent performance in a variety of evaluation benchmarks, they still struggle in complex reasoning tasks which require specific knowledge and multi-hop reasoning. To improve the reasoning abilities, we propose ChatCoT, a tool-augmented chain-of-thought reasoning framework for chat-based LLMs (e.g., ChatGPT). In ChatCoT, we model the chain-of-thought (CoT) reasoning as multi-turn conversations, to utilize tools in a more natural way through chatting. At each turn, LLMs can either interact with tools or perform the reasoning. Our approach can effectively leverage the multi-turn conversation ability of chat-based LLMs, and integrate the thought chain following and tools manipulation in a unified way. Specially, we initialize the early turns of the conversation by the knowledge about tools, tasks, and reasoning format, and propose an iterative tool-augmented reasoning step to perform step-by-step tool-augmented reasoning. The experiment results on two complex reasoning datasets (MATH and HotpotQA) have shown the effectiveness of ChatCoT on complex reasoning tasks, achieving a 7.9% relative improvement over the state-of-the-art baseline.
Anthology ID:
2023.findings-emnlp.985
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:
14777–14790
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.985
DOI:
10.18653/v1/2023.findings-emnlp.985
Bibkey:
Cite (ACL):
Zhipeng Chen, Kun Zhou, Beichen Zhang, Zheng Gong, Xin Zhao, and Ji-Rong Wen. 2023. ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14777–14790, Singapore. Association for Computational Linguistics.
Cite (Informal):
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models (Chen et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-emnlp.985.pdf