POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912338253185024 |
|---|---|
| author | Gan, Chunjing Yang, Dan Hu, Binbin Liu, Ziqi Shen, Yue Zhang, Zhiqiang Wang, Jian Zhou, Jun |
| author_facet | Gan, Chunjing Yang, Dan Hu, Binbin Liu, Ziqi Shen, Yue Zhang, Zhiqiang Wang, Jian Zhou, Jun |
| contents | Large language models (LLMs) have become a disruptive force in the industry, introducing unprecedented capabilities in natural language processing, logical reasoning and so on. However, the challenges of knowledge updates and hallucination issues have limited the application of LLMs in medical scenarios, where retrieval-augmented generation (RAG) can offer significant assistance. Nevertheless, existing retrieve-then-read approaches generally digest the retrieved documents, without considering the timeliness, authoritativeness and commonality of retrieval. We argue that these approaches can be suboptimal, especially in real-world applications where information from different sources might conflict with each other and even information from the same source in different time scale might be different, and totally relying on this would deteriorate the performance of RAG approaches. We propose PolyRAG that carefully incorporate judges from different perspectives and finally integrate the polyviews for retrieval augmented generation in medical applications. Due to the scarcity of real-world benchmarks for evaluation, to bridge the gap we propose PolyEVAL, a benchmark consists of queries and documents collected from real-world medical scenarios (including medical policy, hospital & doctor inquiry and healthcare) with multiple tagging (e.g., timeliness, authoritativeness) on them. Extensive experiments and analysis on PolyEVAL have demonstrated the superiority of PolyRAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14917 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications Gan, Chunjing Yang, Dan Hu, Binbin Liu, Ziqi Shen, Yue Zhang, Zhiqiang Wang, Jian Zhou, Jun Machine Learning Large language models (LLMs) have become a disruptive force in the industry, introducing unprecedented capabilities in natural language processing, logical reasoning and so on. However, the challenges of knowledge updates and hallucination issues have limited the application of LLMs in medical scenarios, where retrieval-augmented generation (RAG) can offer significant assistance. Nevertheless, existing retrieve-then-read approaches generally digest the retrieved documents, without considering the timeliness, authoritativeness and commonality of retrieval. We argue that these approaches can be suboptimal, especially in real-world applications where information from different sources might conflict with each other and even information from the same source in different time scale might be different, and totally relying on this would deteriorate the performance of RAG approaches. We propose PolyRAG that carefully incorporate judges from different perspectives and finally integrate the polyviews for retrieval augmented generation in medical applications. Due to the scarcity of real-world benchmarks for evaluation, to bridge the gap we propose PolyEVAL, a benchmark consists of queries and documents collected from real-world medical scenarios (including medical policy, hospital & doctor inquiry and healthcare) with multiple tagging (e.g., timeliness, authoritativeness) on them. Extensive experiments and analysis on PolyEVAL have demonstrated the superiority of PolyRAG. |
| title | POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.14917 |