Scholarlink

We present BioRAGent, an interactive web-based retrieval-augmented generation (RAG) system for biomedical question answering. The system uses large language models (LLMs) for query expansion, snippet extraction, and answer generation while maintaining transparency through citation links to the source documents and displaying generated queries for further editing. Building on our successful participation in the BioASQ 2024 challenge, we demonstrate how few-shot learning with LLMs can be effectively applied for a professional search setting. The system supports both direct short paragraph style responses and responses with inline citations. Our demo is available online \(^1\) ( https://bioragent.samyateia.de/ ), and the source code is publicly accessible through GitHub \(^2\) ( https://github.com/SamyAteia/BioRAGent ).

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

BioRAGent: A Retrieval-Augmented Generation System for Showcasing Generative Query Expansion and Domain-Specific Search for Scientific Q&A

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Samy Ateia,
  • Udo Kruschwitz

摘要

We present BioRAGent, an interactive web-based retrieval-augmented generation (RAG) system for biomedical question answering. The system uses large language models (LLMs) for query expansion, snippet extraction, and answer generation while maintaining transparency through citation links to the source documents and displaying generated queries for further editing. Building on our successful participation in the BioASQ 2024 challenge, we demonstrate how few-shot learning with LLMs can be effectively applied for a professional search setting. The system supports both direct short paragraph style responses and responses with inline citations. Our demo is available online \(^1\) ( https://bioragent.samyateia.de/ ), and the source code is publicly accessible through GitHub \(^2\) ( https://github.com/SamyAteia/BioRAGent ).