Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning

TL;DR

This paper explores using information retrieval techniques to select examples for prompts, significantly improving spoken language understanding in few-shot learning scenarios without increasing prompt length.

Contribution

It introduces an IR-based example selection method to enhance prompts for SLU tasks, demonstrating improved performance in few-shot settings.

Findings

IR methods significantly improve SLU performance

Enhanced prompts do not increase prompt length

Effective across multiple SLU benchmarks

Abstract

Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken Language Understanding (SLU) approaches to ensure the reliability of the considered system. Current State-of-the-Art SLU techniques rely on large amounts of training data; however, only limited annotated examples are available for specific tasks or languages. In the meantime, instruction-tuned large language models (LLMs) have shown exceptional performance on unseen tasks in a few-shot setting when provided with adequate prompts. In this work, we propose to explore example selection by leveraging Information retrieval (IR) approaches to build an enhanced prompt that is applied to an SLU task. We evaluate the effectiveness of the proposed method on several SLU benchmarks. Experimental results show that lexical IR methods significantly enhance performance without increasing prompt length.