ReFeed: Retrieval Feedback-Guided Dataset Construction for Style-Aware Query Rewriting
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_ | 1866910037639692288 |
|---|---|
| author | Myung, Jiyoon Son, Jungki Lee, Kyungro Park, Jihyeon Han, Joohyung |
| author_facet | Myung, Jiyoon Son, Jungki Lee, Kyungro Park, Jihyeon Han, Joohyung |
| contents | Retrieval systems often fail when user queries differ stylistically or semantically from the language used in domain documents. Query rewriting has been proposed to bridge this gap, improving retrieval by reformulating user queries into semantically equivalent forms. However, most existing approaches overlook the stylistic characteristics of target documents-their domain-specific phrasing, tone, and structure-which are crucial for matching real-world data distributions. We introduce a retrieval feedback-driven dataset generation framework that automatically identifies failed retrieval cases, leverages large language models to rewrite queries in the style of relevant documents, and verifies improvement through re-retrieval. The resulting corpus of (original, rewritten) query pairs enables the training of rewriter models that are explicitly aware of document style and retrieval feedback. This work highlights a new direction in data-centric information retrieval, emphasizing how feedback loops and document-style alignment can enhance the reasoning and adaptability of RAG systems in real-world, domain-specific contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01417 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ReFeed: Retrieval Feedback-Guided Dataset Construction for Style-Aware Query Rewriting Myung, Jiyoon Son, Jungki Lee, Kyungro Park, Jihyeon Han, Joohyung Information Retrieval Retrieval systems often fail when user queries differ stylistically or semantically from the language used in domain documents. Query rewriting has been proposed to bridge this gap, improving retrieval by reformulating user queries into semantically equivalent forms. However, most existing approaches overlook the stylistic characteristics of target documents-their domain-specific phrasing, tone, and structure-which are crucial for matching real-world data distributions. We introduce a retrieval feedback-driven dataset generation framework that automatically identifies failed retrieval cases, leverages large language models to rewrite queries in the style of relevant documents, and verifies improvement through re-retrieval. The resulting corpus of (original, rewritten) query pairs enables the training of rewriter models that are explicitly aware of document style and retrieval feedback. This work highlights a new direction in data-centric information retrieval, emphasizing how feedback loops and document-style alignment can enhance the reasoning and adaptability of RAG systems in real-world, domain-specific contexts. |
| title | ReFeed: Retrieval Feedback-Guided Dataset Construction for Style-Aware Query Rewriting |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2603.01417 |