让医生快速查到更新的癌症指南并看清变化，避免误用过时信息。
SentryLine: Evidence-Grounded Question Answering over Evolving Documents in Oncology Care
- 用分层检索无向量方法精准定位指南片段
- 回答含引用、时间验证和更新提醒，支持多轮对话
- 专为临床场景设计，适合肿瘤科医生日常决策
肿瘤学诊疗面临生物医学证据快速演进的压力。美国临床肿瘤学会（ASCO）通过动态指南应对，但版本迭代频繁，导致推荐内容随时可能变更。我们提出SENTRYLINE——一种面向动态指南的临床问答系统。该系统采用无向量分层RAG管道检索指南段落，返回角色定制答案，并附带内联引用、事实与时间验证报告，以及指南更新漂移检测提示。我们构建了ASCOBENCH基准，包含405个三轮对话，涵盖四类问题，由专家标注金标准答案。在测试集上，使用大模型评分框架评估，相比五种基线方法，三类生成模型均表现更优，尤其在需多跳推理与角色适配的复杂问题上提升显著。
原文摘要 · Abstract (English)
Oncology care operates at constant pressure of absorbing rapidly evolving evidence base in biomedicine. The American Society of Clinical Oncology (ASCO) addresses this through living guidelines, but the format introduces a new burden: any recommendation can change at any point, across multiple versioned documents. We present SENTRYLINE, a living guideline-aware clinical question answering system. SENTRYLINE retrieves guideline passages through a vectorless hierarchical RAG pipeline and returns a role-specific answer with inline citations, factual and temporal verification reports, and drift detection notes that surface when a guideline has been updated. We construct ASCOBENCH, a benchmark of 405 three-turn conversations across four question categories with gold answers from expert annotators(clinicians), and use test set to evaluate SENTRYLINE against five baselines under an LLM-as-judge framework. Experiments across three generation backbones show consistent improvements over four retrieval baselines and ASCO's guideline assistant, with particularly strong gains on Reasoning and Role-Specific questions where multi-hop synthesis and register adaptation are required
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。