Aligned Query Expansion: Efficient Query Expansion for Information Retrieval through LLM Alignment

TL;DR

This paper introduces Aligned Query Expansion (AQE), a novel method that fine-tunes large language models to generate more effective query expansions for passage retrieval, reducing costs and improving retrieval accuracy.

Contribution

AQE leverages LLM alignment techniques to directly optimize query expansions for retrieval, eliminating the costly generate-then-filter process and enhancing effectiveness.

Findings

AQE outperforms baseline models in retrieval tasks.

AQE improves effectiveness in both in-domain and out-of-domain settings.

AQE reduces computational costs compared to previous methods.

Abstract

With the breakthroughs in large language models (LLMs), query generation techniques that expand documents and queries with related terms are becoming increasingly popular in the information retrieval field. Such techniques have been shown to improve the effectiveness of traditional lexical retrieval methods by dealing with the vocabulary mismatch problem. Recent work has found that generating queries with a greedy decoding strategy can produce sub-optimal queries, including hallucinations, and proposed to filter out queries before expansion. This `generate-then-filter' approach is costly, as it requires generating multiple queries and applying a relevance model to all of them and does not teach the LLM which of the generated queries is more effective for expansion. To overcome such limitations, we propose Aligned Query Expansion (AQE), a novel approach to enhance query expansion for passage retrieval in open-domain question answering. AQE leverages recent techniques in LLM alignment to fine-tune models for generating query expansions that directly optimize the effectiveness of the retrieval task, eliminating the need for additional filtering steps. This alignment ensures that queries are more relevant, reducing computational costs while improving retrieval effectiveness. Empirical evaluations show that AQE outperforms baseline models for query expansion in both in-domain and out-of-domain settings, demonstrating significant improvements in retrieval effectiveness.