PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908787909066752 |
|---|---|
| author | Kweon, Wonbin Tian, Runchu Kang, SeongKu Jiang, Pengcheng Lu, Zhiyong Han, Jiawei Yu, Hwanjo |
| author_facet | Kweon, Wonbin Tian, Runchu Kang, SeongKu Jiang, Pengcheng Lu, Zhiyong Han, Jiawei Yu, Hwanjo |
| contents | Scientific document retrieval is a critical task for enabling knowledge discovery and supporting research across diverse domains. However, existing dense retrieval methods often struggle to capture fine-grained scientific concepts in texts due to their reliance on holistic embeddings and limited domain understanding. Recent approaches leverage large language models (LLMs) to extract fine-grained semantic entities and enhance semantic matching, but they typically treat entities as independent fragments, overlooking the multi-faceted nature of scientific concepts. To address this limitation, we propose Pairwise Semantic Matching (PairSem), a framework that represents relevant semantics as entity-aspect pairs, capturing complex, multi-faceted scientific concepts. PairSem is unsupervised, base retriever-agnostic, and plug-and-play, enabling precise and context-aware matching without requiring query-document labels or entity annotations. Extensive experiments on multiple datasets and retrievers demonstrate that PairSem significantly improves retrieval performance, highlighting the importance of modeling multi-aspect semantics in scientific information retrieval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09897 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval Kweon, Wonbin Tian, Runchu Kang, SeongKu Jiang, Pengcheng Lu, Zhiyong Han, Jiawei Yu, Hwanjo Information Retrieval Scientific document retrieval is a critical task for enabling knowledge discovery and supporting research across diverse domains. However, existing dense retrieval methods often struggle to capture fine-grained scientific concepts in texts due to their reliance on holistic embeddings and limited domain understanding. Recent approaches leverage large language models (LLMs) to extract fine-grained semantic entities and enhance semantic matching, but they typically treat entities as independent fragments, overlooking the multi-faceted nature of scientific concepts. To address this limitation, we propose Pairwise Semantic Matching (PairSem), a framework that represents relevant semantics as entity-aspect pairs, capturing complex, multi-faceted scientific concepts. PairSem is unsupervised, base retriever-agnostic, and plug-and-play, enabling precise and context-aware matching without requiring query-document labels or entity annotations. Extensive experiments on multiple datasets and retrievers demonstrate that PairSem significantly improves retrieval performance, highlighting the importance of modeling multi-aspect semantics in scientific information retrieval. |
| title | PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2510.09897 |