Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Yinger, Cai, Hui, Song, Xeirui, Chen, Yicheng, Sun, Rui, Zheng, Jing
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913239324950528
author Zhang, Yinger
Cai, Hui
Song, Xeirui
Chen, Yicheng
Sun, Rui
Zheng, Jing
author_facet Zhang, Yinger
Cai, Hui
Song, Xeirui
Chen, Yicheng
Sun, Rui
Zheng, Jing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_04474
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning
Zhang, Yinger
Cai, Hui
Song, Xeirui
Chen, Yicheng
Sun, Rui
Zheng, Jing
Software Engineering
Artificial Intelligence
Programming Languages
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.
title Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning
topic Software Engineering
Artificial Intelligence
Programming Languages
url https://arxiv.org/abs/2310.04474