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

05/23/2023
by   Zhipeng Chen, et al.
0

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. 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 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 6.8% relative improvement over the state-of-the-art baseline. Our code and data are available at: <https://github.com/RUCAIBOX/ChatCoT>.

READ FULL TEXT

page 4

page 9

research
06/04/2023

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

Chain-of-thought prompting (CoT) and tool augmentation have been validat...
research
05/26/2023

MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting

Large language models (LLMs) have achieved impressive performance on var...
research
07/11/2023

Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

Human intelligence thrives on the concept of cognitive synergy, where co...
research
07/04/2023

Insert-expansions for Tool-enabled Conversational Agents

This paper delves into an advanced implementation of Chain-of-Thought-Pr...
research
11/15/2022

Reasoning Circuits: Few-shot Multihop Question Generation with Structured Rationales

Multi-hop Question Generation is the task of generating questions which ...
research
05/23/2023

Automatic Model Selection with Large Language Models for Reasoning

Chain-of-Thought and Program-Aided Language Models represent two distinc...
research
08/29/2023

When Do Program-of-Thoughts Work for Reasoning?

The reasoning capabilities of Large Language Models (LLMs) play a pivota...

Please sign up or login with your details

Forgot password? Click here to reset