Multi-Facet Blending for Faceted Query-by-Example Retrieval

TL;DR

This paper introduces FaBle, a modular data augmentation method for faceted query-by-example retrieval, which synthesizes facet-specific training data using large language models, improving retrieval in new domains.

Contribution

FaBle is a novel augmentation technique that decomposes documents into facets and recomposes them to generate facet-aware training data without pre-labeled facets.

Findings

FaBle improves facet-conditioned embedding quality.

Augmentation enhances retrieval performance on a new educational dataset.

Method reduces reliance on domain-specific facet labels.

Abstract

With the growing demand to fit fine-grained user intents, faceted query-by-example (QBE), which retrieves similar documents conditioned on specific facets, has gained recent attention. However, prior approaches mainly depend on document-level comparisons using basic indicators like citations due to the lack of facet-level relevance datasets; yet, this limits their use to citation-based domains and fails to capture the intricacies of facet constraints. In this paper, we propose a multi-facet blending (FaBle) augmentation method, which exploits modularity by decomposing and recomposing to explicitly synthesize facet-specific training sets. We automatically decompose documents into facet units and generate (ir)relevant pairs by leveraging LLMs' intrinsic distinguishing capabilities; then, dynamically recomposing the units leads to facet-wise relevance-informed document pairs. Our modularization eliminates the need for pre-defined facet knowledge or labels. Further, to prove the FaBle's efficacy in a new domain beyond citation-based scientific paper retrieval, we release a benchmark dataset for educational exam item QBE. FaBle augmentation on 1K documents remarkably assists training in obtaining facet conditional embeddings.