逆向链:一种让大语言模型掌握多API规划的通用规则
Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning
AI总结:
本文提出Reverse Chain方法,通过逆向推理通用规则让大语言模型仅凭提示词即可完成多API规划与调用,并发布组合式多工具任务数据集验证其有效性。
摘要:
尽管使大语言模型能够实现函数调用(即API)可以极大地提升大语言模型(LLMs)的性能,但由于不同API之间复杂的关系,函数调用仍然是一项具有挑战性的任务,尤其是在没有微调的上下文学习环境中。本文介绍了“Reverse Chain”(逆向链),一种可控的、目标驱动的方法,旨在仅通过提示词赋予LLMs操作外部API的能力。考虑到大多数LLMs的工具使用能力有限,Reverse Chain将LLMs限制在执行简单任务上,例如API选择和参数补全。此外,为了管理可控的多函数调用,Reverse Chain采用了一种基于逆向推理过程的通用规则。该规则决定了何时进行API选择或参数补全。为了评估LLMs的多工具使用能力,我们发布了一个组合式多工具任务数据集,可在\url{https://anonymous.4open.science/r/reverse-chain-8681}获取。大量数值实验验证了Reverse Chain在管理多个API调用方面的卓越能力。
英文摘要:
While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of Large Language Models (LLMs), function calling is still a challenging task due to the complicated relations between different APIs, especially in a context-learning setting without fine-tuning. This paper introduces ``Reverse Chain'', a controllable, target-driven approach designed to empower LLMs with the capability to operate external APIs only via prompts. Recognizing that most LLMs have limited tool-use capabilities, Reverse Chain limits LLMs to executing simple tasks, e.g., API Selection and Argument Completion. Furthermore, to manage a controllable multi-function calling, Reverse Chain adopts a generic rule based on a backward reasoning process. This rule determines when to do API selection or Argument completion. To evaluate the multi-tool-use capability of LLMs, we have released a compositional multi-tool task dataset, available at \url{https://anonymous.4open.science/r/reverse-chain-8681}. Extensive numerical experiments validate the remarkable proficiency of Reverse Chain in managing multiple API calls.
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。