ReFormeR: Learning and Applying Explicit Query Reformulation Patterns

TL;DR

ReFormeR introduces a pattern-guided method for query reformulation that leverages explicit reformulation patterns to improve retrieval effectiveness across multiple datasets.

Contribution

It develops a transferable pattern library for query reformulation, guiding large language models to produce targeted and effective query modifications.

Findings

Consistent improvements over classical feedback methods.

Outperforms recent LLM-based reformulation approaches.

Effective across multiple TREC datasets.

Abstract

We present ReFormeR, a pattern-guided approach for query reformulation. Instead of prompting a language model to generate reformulations of a query directly, ReFormeR first elicits short reformulation patterns from pairs of initial queries and empirically stronger reformulations, consolidates them into a compact library of transferable reformulation patterns, and then selects an appropriate reformulation pattern for a new query given its retrieval context. The selected pattern constrains query reformulation to controlled operations such as sense disambiguation, vocabulary grounding, or discriminative facet addition, to name a few. As such, our proposed approach makes the reformulation policy explicit through these reformulation patterns, guiding the LLM towards targeted and effective query reformulations. Our extensive experiments on TREC DL 2019, DL 2020, and DL Hard show consistent improvements over classical feedback methods and recent LLM-based query reformulation and expansion approaches.