PEToolLLM: Towards Personalized Tool Learning in Large Language Models

TL;DR

This paper introduces PEToolLLaMA, a framework that enables large language models to learn personalized tool usage by leveraging user interaction history, supported by a new benchmark PEToolBench for evaluation.

Contribution

The paper formulates personalized tool learning for LLMs, creates PEToolBench benchmark, and proposes PEToolLLaMA framework for adapting LLMs to personalized tool use.

Findings

PEToolLLaMA outperforms existing LLMs on PEToolBench.

The framework effectively incorporates user preferences.

Extensive experiments validate the approach's superiority.

Abstract

Tool learning has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools. Existing tool learning studies primarily focus on the general-purpose tool-use capability, which addresses explicit user requirements in instructions. However, they overlook the importance of personalized tool-use capability, leading to an inability to handle implicit user preferences. To address the limitation, we first formulate the task of personalized tool learning, which integrates user's interaction history towards personalized tool usage. To fill the gap of missing benchmarks, we construct PEToolBench, featuring diverse user preferences reflected in interaction history under three distinct personalized settings, and encompassing a wide range of tool-use scenarios. Moreover, we propose a framework PEToolLLaMA to adapt LLMs to the personalized tool learning task, which is trained through supervised fine-tuning and direct preference optimization. Extensive experiments on PEToolBench demonstrate the superiority of PEToolLLaMA over existing LLMs.