GuRE:Generative Query REwriter for Legal Passage Retrieval
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915526851166208 |
|---|---|
| author | Kim, Daehee Kang, Deokhyung Kim, Jonghwi Ryu, Sangwon Lee, Gary Geunbae |
| author_facet | Kim, Daehee Kang, Deokhyung Kim, Jonghwi Ryu, Sangwon Lee, Gary Geunbae |
| contents | Legal Passage Retrieval (LPR) systems are crucial as they help practitioners save time when drafting legal arguments. However, it remains an underexplored avenue. One primary reason is the significant vocabulary mismatch between the query and the target passage. To address this, we propose a simple yet effective method, the Generative query REwriter (GuRE). We leverage the generative capabilities of Large Language Models (LLMs) by training the LLM for query rewriting. "Rewritten queries" help retrievers to retrieve target passages by mitigating vocabulary mismatch. Experimental results show that GuRE significantly improves performance in a retriever-agnostic manner, outperforming all baseline methods. Further analysis reveals that different training objectives lead to distinct retrieval behaviors, making GuRE more suitable than direct retriever fine-tuning for real-world applications. Codes are avaiable at github.com/daehuikim/GuRE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12950 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GuRE:Generative Query REwriter for Legal Passage Retrieval Kim, Daehee Kang, Deokhyung Kim, Jonghwi Ryu, Sangwon Lee, Gary Geunbae Computation and Language Legal Passage Retrieval (LPR) systems are crucial as they help practitioners save time when drafting legal arguments. However, it remains an underexplored avenue. One primary reason is the significant vocabulary mismatch between the query and the target passage. To address this, we propose a simple yet effective method, the Generative query REwriter (GuRE). We leverage the generative capabilities of Large Language Models (LLMs) by training the LLM for query rewriting. "Rewritten queries" help retrievers to retrieve target passages by mitigating vocabulary mismatch. Experimental results show that GuRE significantly improves performance in a retriever-agnostic manner, outperforming all baseline methods. Further analysis reveals that different training objectives lead to distinct retrieval behaviors, making GuRE more suitable than direct retriever fine-tuning for real-world applications. Codes are avaiable at github.com/daehuikim/GuRE. |
| title | GuRE:Generative Query REwriter for Legal Passage Retrieval |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.12950 |