Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911656005599232 |
|---|---|
| author | Li, Minghan Lv, Xinxuan Zou, Junjie Chen, Tongna Zhang, Chao An, Suchao Nie, Ercong Zhou, Guodong |
| author_facet | Li, Minghan Lv, Xinxuan Zou, Junjie Chen, Tongna Zhang, Chao An, Suchao Nie, Ercong Zhou, Guodong |
| contents | Modern information retrieval must reconcile short, ambiguous queries with increasingly diverse and dynamic corpora. Query expansion (QE) remains a core technique for mitigating vocabulary mismatch, but its design space has been reshaped by pre-trained and large language models (PLMs/LLMs). This survey reviews QE methods in the PLM/LLM era and provides a unified view of the emerging landscape. We first summarize how different model families enable new expansion behaviors, including stronger contextualization, more controllable generation, and instruction-following. We then organize recent techniques along four complementary design dimensions: where expansion is injected in the pipeline, how it is grounded and interacts with corpus evidence, how it is learned or aligned, and how structured knowledge such as knowledge graphs is incorporated. Beyond taxonomy, we synthesize application patterns and deployment considerations across representative retrieval settings, highlighting practical trade-offs among effectiveness, controllability, grounding quality, and operating cost. Finally, we outline open challenges and future directions toward more reliable, safe, efficient, and continually adaptive QE under real-world constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07794 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey Li, Minghan Lv, Xinxuan Zou, Junjie Chen, Tongna Zhang, Chao An, Suchao Nie, Ercong Zhou, Guodong Information Retrieval Modern information retrieval must reconcile short, ambiguous queries with increasingly diverse and dynamic corpora. Query expansion (QE) remains a core technique for mitigating vocabulary mismatch, but its design space has been reshaped by pre-trained and large language models (PLMs/LLMs). This survey reviews QE methods in the PLM/LLM era and provides a unified view of the emerging landscape. We first summarize how different model families enable new expansion behaviors, including stronger contextualization, more controllable generation, and instruction-following. We then organize recent techniques along four complementary design dimensions: where expansion is injected in the pipeline, how it is grounded and interacts with corpus evidence, how it is learned or aligned, and how structured knowledge such as knowledge graphs is incorporated. Beyond taxonomy, we synthesize application patterns and deployment considerations across representative retrieval settings, highlighting practical trade-offs among effectiveness, controllability, grounding quality, and operating cost. Finally, we outline open challenges and future directions toward more reliable, safe, efficient, and continually adaptive QE under real-world constraints. |
| title | Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2509.07794 |