Improving Health Literacy through Lay Summarization of Radiological Reports: An Evaluation of BioNER and Retrieval-Augmented Generation

  • 类型:arxiv
  • 标识:2609.02396
  • 链接:http://arxiv.org/abs/2609.02396v1
  • 主分类:rag
  • 形态:benchmark
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:This study investigates the extent to which Retrieval-Augmented Generation and Named Entity Recognition improve the quality, factual consistency, and readability of automatically generated lay summaries compared with standard LLM-based generation.
  • OpenAlex ID:W7207877279
  • OpenAlex DOI:10.48550/arxiv.2609.02396
  • DOI:10.48550/arxiv.2609.02396
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2609.02396
  • OpenAlex更新:2026-09-05
  • 副分类:evaluation
  • 待LLM分类:否
  • 标题中文:通过放射学报告的大众化摘要提升健康素养:BioNER 与检索增强生成的评估
  • TLDR中文:本研究探讨了相较于标准 LLM 生成方式,RAG 与命名实体识别在多大程度上能提升自动生成通俗摘要的质量、事实一致性及可读性。
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-03-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • [S2 enrich]