Tool Retrieval Bridge: Aligning Vague Instructions with Retriever Preferences via Bridge Model

TL;DR

This paper introduces VGToolBench, a benchmark for vague instructions, and proposes the Tool Retrieval Bridge (TRB) to improve tool retrieval accuracy by rewriting vague instructions into specific ones, significantly enhancing retrieval performance.

Contribution

The paper presents a new benchmark for vague instructions and a bridge model that rewrites instructions to improve tool retrieval in real-world scenarios.

Findings

TRB improves retrieval performance across multiple baselines.

Using TRB, BM25's NDCG score increases from 9.73 to 19.59.

Vague instructions negatively impact tool retrieval accuracy.

Abstract

Tool learning has emerged as a promising paradigm for large language models (LLMs) to address real-world challenges. Due to the extensive and irregularly updated number of tools, tool retrieval for selecting the desired tool subset is essential. However, current tool retrieval methods are usually based on academic benchmarks containing overly detailed instructions (e.g., specific API names and parameters), while real-world instructions are more vague. Such a discrepancy would hinder the tool retrieval in real-world applications. In this paper, we first construct a new benchmark, VGToolBench, to simulate human vague instructions. Based on this, we conduct a series of preliminary analyses and find that vague instructions indeed damage the performance of tool retrieval. To this end, we propose a simple-yet-effective Tool Retrieval Bridge (TRB) approach to boost the performance of tool retrieval for vague instructions. The principle of TRB is to introduce a bridge model to rewrite the vague instructions into more specific ones and alleviate the gap between vague instructions and retriever preferences.We conduct extensive experiments under multiple commonly used retrieval settings, and the results show that TRB effectively mitigates the ambiguity of vague instructions while delivering consistent and substantial improvements across all baseline retrievers. For example, with the help of TRB, BM25 achieves a relative improvement of up to 111.51%, i.e., increasing the average NDCG score from 9.73 to 19.59. The source code and models are publicly available at https://github.com/kfchenhn/TRB.