Paper Detail

ReFormeR: Learning and Applying Explicit Query Reformulation Patterns

Amin Bigdeli, Mert Incesu, Negar Arabzadeh, Charles L. A. Clarke, Ebrahim Bagheri

arxiv Score 5.8

Published 2026-04-01 · First seen 2026-04-04

General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{bigdeli2026reformer,
  title = {ReFormeR: Learning and Applying Explicit Query Reformulation Patterns},
  author = {Amin Bigdeli and Mert Incesu and Negar Arabzadeh and Charles L. A. Clarke and Ebrahim Bagheri},
  year = {2026},
  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 r},
  url = {https://arxiv.org/abs/2604.01417},
  keywords = {cs.IR, cs.CL},
  eprint = {2604.01417},
  archiveprefix = {arXiv},
}

Metadata

{}