Enhanced Facet Generation with LLM Editing

TL;DR

This paper introduces a new framework for facet generation in information retrieval that relies solely on queries, utilizing multi-task learning and combining large language models with small models to improve performance without external search engines.

Contribution

It proposes two novel strategies—multi-task learning for SERP prediction and LLM-small model combination—that enable effective facet prediction without external search engine reliance.

Findings

Performance improves with combined LLM and small model.

Framework predicts facets using only queries, avoiding external search engines.

Deep understanding of queries achieved through multi-task learning.

Abstract

In information retrieval, facet identification of a user query is an important task. If a search service can recognize the facets of a user's query, it has the potential to offer users a much broader range of search results. Previous studies can enhance facet prediction by leveraging retrieved documents and related queries obtained through a search engine. However, there are challenges in extending it to other applications when a search engine operates as part of the model. First, search engines are constantly updated. Therefore, additional information may change during training and test, which may reduce performance. The second challenge is that public search engines cannot search for internal documents. Therefore, a separate search system needs to be built to incorporate documents from private domains within the company. We propose two strategies that focus on a framework that can predict facets by taking only queries as input without a search engine. The first strategy is multi-task learning to predict SERP. By leveraging SERP as a target instead of a source, the proposed model deeply understands queries without relying on external modules. The second strategy is to enhance the facets by combining Large Language Model (LLM) and the small model. Overall performance improves when small model and LLM are combined rather than facet generation individually.