Saved in:
Bibliographic Details
Main Authors: Gui, Anchun, Li, Jian, Dai, Yong, Du, Nan, Xiao, Han
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.16696
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910580068057088
author Gui, Anchun
Li, Jian
Dai, Yong
Du, Nan
Xiao, Han
author_facet Gui, Anchun
Li, Jian
Dai, Yong
Du, Nan
Xiao, Han
contents Tool-augmented large language models (LLMs) are attracting widespread attention when accessing up-to-date knowledge and alleviating hallucination issues. Nowadays, advanced closed-source LLMs (e.g., ChatGPT) have demonstrated surprising tool-usage capabilities through prompting and in-context learning techniques. To empower the capabilities of open-source LLMs (e.g., LLaMA) in manipulating tools, current efforts focus on either template-driven or token-triggered tool-usage. However, the former hampers LLMs' flexibility to address diverse user's queries due to constrained tool interactions, while the latter limits the generalizability when engaging with new tools, since tool-usage learning is based on task- and tool-specific datasets. To alleviate these concerns, in this paper, we propose a decision-aware and generalizable tool-usage framework (DEER). Specifically, we first construct the tool-usage samples with multiple decision branches via an automatic generation pipeline, thereby inspiring the decision-making awareness of LLMs under diverse scenarios. Meanwhile, we propose a novel tool sampling strategy to enhance the generalizability of LLMs over unseen tools. Extensive experiments demonstrate that our proposed DEER is effective and significantly outperforms baselines across various datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2402_16696
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models
Gui, Anchun
Li, Jian
Dai, Yong
Du, Nan
Xiao, Han
Computation and Language
Tool-augmented large language models (LLMs) are attracting widespread attention when accessing up-to-date knowledge and alleviating hallucination issues. Nowadays, advanced closed-source LLMs (e.g., ChatGPT) have demonstrated surprising tool-usage capabilities through prompting and in-context learning techniques. To empower the capabilities of open-source LLMs (e.g., LLaMA) in manipulating tools, current efforts focus on either template-driven or token-triggered tool-usage. However, the former hampers LLMs' flexibility to address diverse user's queries due to constrained tool interactions, while the latter limits the generalizability when engaging with new tools, since tool-usage learning is based on task- and tool-specific datasets. To alleviate these concerns, in this paper, we propose a decision-aware and generalizable tool-usage framework (DEER). Specifically, we first construct the tool-usage samples with multiple decision branches via an automatic generation pipeline, thereby inspiring the decision-making awareness of LLMs under diverse scenarios. Meanwhile, we propose a novel tool sampling strategy to enhance the generalizability of LLMs over unseen tools. Extensive experiments demonstrate that our proposed DEER is effective and significantly outperforms baselines across various datasets.
title Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2402.16696