ReFormeR: Learning and Applying Explicit Query Reformulation Patterns
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911562167484416 |
|---|---|
| author | Bigdeli, Amin Incesu, Mert Arabzadeh, Negar Clarke, Charles L. A. Bagheri, Ebrahim |
| author_facet | Bigdeli, Amin Incesu, Mert Arabzadeh, Negar Clarke, Charles L. A. Bagheri, Ebrahim |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01417 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ReFormeR: Learning and Applying Explicit Query Reformulation Patterns Bigdeli, Amin Incesu, Mert Arabzadeh, Negar Clarke, Charles L. A. Bagheri, Ebrahim Information Retrieval Computation and Language 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. |
| title | ReFormeR: Learning and Applying Explicit Query Reformulation Patterns |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2604.01417 |