Abstract
This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first generates pseudo-documents by few-shot prompting large language models (LLMs), and then expands the query with generated pseudo documents. LLMs are trained on web-scale text corpora and are adept at knowledge memorization. The pseudo-documents from LLMs often contain highly relevant information that can aid in query disambiguation and guide the retrievers. Experimental results demonstrate that query2doc boosts the performance of BM25 by 3% to 15% on ad-hoc IR datasets, such as MS-MARCO and TREC DL, without any model fine-tuning. Furthermore, our method also benefits state-of-the-art dense retrievers in terms of both in-domain and out-of-domain results.- Anthology ID:
- 2023.emnlp-main.585
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9414–9423
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.585
- DOI:
- 10.18653/v1/2023.emnlp-main.585
- Cite (ACL):
- Liang Wang, Nan Yang, and Furu Wei. 2023. Query2doc: Query Expansion with Large Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9414–9423, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Query2doc: Query Expansion with Large Language Models (Wang et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.emnlp-main.585.pdf