ChatCoT：面向聊天式大语言模型的工具增强思维链推理
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
AI总结：
针对大语言模型在复杂推理任务上的不足，提出面向聊天式LLM的工具增强思维链框架ChatCoT，将推理建模为多轮对话，通过迭代工具增强步骤逐步推理，在MATH和HotpotQA数据集上较最优基线提升7.9%。
摘要：
尽管大语言模型（LLM）已在各类评估基准中取得出色表现，但在需要特定知识与多跳推理的复杂推理任务上仍存在不足。为提升推理能力，我们提出ChatCoT，一种面向聊天式LLM（如ChatGPT）的工具增强思维链推理框架。在ChatCoT中，我们将思维链（CoT）推理建模为多轮对话，从而通过聊天以更自然的方式调用工具。每一轮中，LLM既可以与工具交互，也可以执行推理。我们的方法能有效利用聊天式LLM的多轮对话能力，将思维链跟进与工具操作整合到统一框架中。具体而言，我们通过工具、任务及推理格式相关知识初始化对话的早期轮次，并提出迭代式工具增强推理步骤，以开展逐步的工具增强推理。在两个复杂推理数据集（MATH和HotpotQA）上的实验结果证明了ChatCoT在复杂推理任务上的有效性，相比现有最优基线取得了7.9%的相对提升。我们的代码与数据可在以下链接获取：https://github.com/RUCAIBOX/ChatCoT。
英文摘要：
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. Our code and data are available at: \url{https://github.com/RUCAIBOX/ChatCoT}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
