Crafting the Path: Robust Query Rewriting for Information Retrieval
Query rewriting aims to generate a new query that can complement the original query to improve the information retrieval system. Recent studies on query rewriting, such as query2doc, query2expand and querey2cot, rely on the internal knowledge of Large Language Models (LLMs) to generate a relevant pa...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10870252/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859631375515648 |
|---|---|
| author | Ingeol Baek Jimin Lee Joonho Yang Hwanhee Lee |
| author_facet | Ingeol Baek Jimin Lee Joonho Yang Hwanhee Lee |
| author_sort | Ingeol Baek |
| collection | DOAJ |
| description | Query rewriting aims to generate a new query that can complement the original query to improve the information retrieval system. Recent studies on query rewriting, such as query2doc, query2expand and querey2cot, rely on the internal knowledge of Large Language Models (LLMs) to generate a relevant passage to add information to the query. Nevertheless, the efficacy of these methodologies may markedly decline in instances where the requisite knowledge is not encapsulated within the model’s intrinsic parameters. In this paper, we propose a novel structured query rewriting method called Crafting The Path tailored for retrieval systems. Crafting The Path involves a three-step process that crafts query-related information necessary for finding the passages to be searched in each step. Specifically, the Crafting The Path begins with Query Concept Comprehension, proceeds to Query Type Identification, and finally conducts Expected Answer Extraction. Experimental results show that our method outperforms previous rewriting methods, especially in less familiar domains for LLMs. We demonstrate that our method is less dependent on the internal parameter knowledge of the model and generates queries with fewer factual inaccuracies. Furthermore, we observe that Crafting The Path demonstrates superior performance in the retrieval-augmented generation scenarios. |
| format | Article |
| id | doaj-art-a80dc6b2b43c41858a42902c9378fef4 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a80dc6b2b43c41858a42902c9378fef42025-02-11T00:01:26ZengIEEEIEEE Access2169-35362025-01-0113241712418010.1109/ACCESS.2025.353866510870252Crafting the Path: Robust Query Rewriting for Information RetrievalIngeol Baek0Jimin Lee1Joonho Yang2Hwanhee Lee3https://orcid.org/0000-0002-9367-9811Department of Artificial Intelligence, Chung-Ang University, Seoul, South KoreaDepartment of Artificial Intelligence, Chung-Ang University, Seoul, South KoreaDepartment of Artificial Intelligence, Chung-Ang University, Seoul, South KoreaDepartment of Artificial Intelligence, Chung-Ang University, Seoul, South KoreaQuery rewriting aims to generate a new query that can complement the original query to improve the information retrieval system. Recent studies on query rewriting, such as query2doc, query2expand and querey2cot, rely on the internal knowledge of Large Language Models (LLMs) to generate a relevant passage to add information to the query. Nevertheless, the efficacy of these methodologies may markedly decline in instances where the requisite knowledge is not encapsulated within the model’s intrinsic parameters. In this paper, we propose a novel structured query rewriting method called Crafting The Path tailored for retrieval systems. Crafting The Path involves a three-step process that crafts query-related information necessary for finding the passages to be searched in each step. Specifically, the Crafting The Path begins with Query Concept Comprehension, proceeds to Query Type Identification, and finally conducts Expected Answer Extraction. Experimental results show that our method outperforms previous rewriting methods, especially in less familiar domains for LLMs. We demonstrate that our method is less dependent on the internal parameter knowledge of the model and generates queries with fewer factual inaccuracies. Furthermore, we observe that Crafting The Path demonstrates superior performance in the retrieval-augmented generation scenarios.https://ieeexplore.ieee.org/document/10870252/Information retrievalquery rewritingretrieval-augmented generationlarge language model |
| spellingShingle | Ingeol Baek Jimin Lee Joonho Yang Hwanhee Lee Crafting the Path: Robust Query Rewriting for Information Retrieval IEEE Access Information retrieval query rewriting retrieval-augmented generation large language model |
| title | Crafting the Path: Robust Query Rewriting for Information Retrieval |
| title_full | Crafting the Path: Robust Query Rewriting for Information Retrieval |
| title_fullStr | Crafting the Path: Robust Query Rewriting for Information Retrieval |
| title_full_unstemmed | Crafting the Path: Robust Query Rewriting for Information Retrieval |
| title_short | Crafting the Path: Robust Query Rewriting for Information Retrieval |
| title_sort | crafting the path robust query rewriting for information retrieval |
| topic | Information retrieval query rewriting retrieval-augmented generation large language model |
| url | https://ieeexplore.ieee.org/document/10870252/ |
| work_keys_str_mv | AT ingeolbaek craftingthepathrobustqueryrewritingforinformationretrieval AT jiminlee craftingthepathrobustqueryrewritingforinformationretrieval AT joonhoyang craftingthepathrobustqueryrewritingforinformationretrieval AT hwanheelee craftingthepathrobustqueryrewritingforinformationretrieval |