SentryLine: Evidence-Grounded Question Answering over Evolving Documents in Oncology Care

• URL: http://arxiv.org/abs/2609.08364v1
• Date: Tue, 08 Sep 2026 07:33:01 GMT
• Title: SentryLine: Evidence-Grounded Question Answering over Evolving Documents in Oncology Care
• Abstract summary: We present SENTRYLINE, a living guideline-aware clinical question answering system.<n>We construct ASCOBENCH, a benchmark of 405 three-turn conversations across four question categories with gold answers from expert annotators(clinicians)<n>Experiments across three generation backbones show consistent improvements over four retrieval baselines and ASCO's guideline assistant.
• Score: 5.871683154602689
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress [130.58520199343707]
  PaperDoctor is an agent framework for pre-submission feedback with three key innovations.<n>First, a holistic hierarchical framework evaluates writing, layout, references, code, theory, prior work, and experiments.<n>Second, each finding contains an observation, a pointer to specific evidence such as a sentence, equation, or code line, and a revision suggestion.<n>Third, PaperDoctor selectively rebuilds and reruns experiments based on claim importance and compute budget.
  arXiv  Detail & Related papers  (2026-09-15T11:08:11Z)
• Case2Flow: Bridging Patient Cases and Guideline Flowcharts through Multimodal Retrieval [65.99409194536337]
  Case2Flow is a task designed to retrieve the most relevant guideline flowchart for a given patient case.<n> FlowAtlas is a curated corpus of 202 flowcharts extracted from 2,080 medical guidelines.<n> CRISP is a training-free scoring method that sharpens late-interaction retrieval by suppressing uninformative patches.
  arXiv  Detail & Related papers  (2026-08-26T21:27:22Z)
• Grounded in Consensus, In Step With Emerging Science: A Consensus-Anchored Multi-Corpus Clinical Chatbot for Long COVID [1.8229646064376668]
  Long COVID (LC) poses a challenge for clinical decision support because relevant evidence is distributed across sources with different update cycles, evidentiary roles, and levels of clinical maturity.<n>We present a clinician-facing robot that organizes four sources within a retrieval-augmented workflow.
  arXiv  Detail & Related papers  (2026-07-27T19:57:23Z)
• Hierarchical Evidence-Driven Reasoning for Long Document Understanding [95.51688464037096]
  We introduce HIEVI-RAG, a hierarchical, evidence-driven multimodal RAG framework for closed-domain document understanding.<n>Our framework significantly outperforms existing open-source baselines and exceeds the strongest reported baseline by an average of 8.05% in accuracy.
  arXiv  Detail & Related papers  (2026-07-06T03:08:28Z)
• When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering [10.478229476671949]
  Most medical large language models (LLMs) are trained to encode common, guideline-focused medical knowledge in their parameters.<n>We introduce OGCaReBench, a free-form retrieval-focused benchmark aimed at evaluating LLMs at answering clinical questions that require going beyond typical guidelines.<n>Our experiments reveal that even the best-performing baseline (GPT-5.2) correctly answers only 56% of our benchmark with specialized models only reaching 42%.
  arXiv  Detail & Related papers  (2026-05-20T23:04:48Z)
• HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering [4.835744579415159]
  This paper presents the system developed by the HealthNLP_Retrievers team for this task.<n>The proposed approach uses a multi-stage cascaded pipeline powered by the Gemini 2.5 Pro large language model.<n>Our architecture comprises four integrated modules: (1) a few-shot query reformulation unit which summarizes patient queries; (2) a verbose-based evidence scorer which ranks clinical sentences to recall; and (3) a grounded response generator which synthesizes professional-caliber answers.
  arXiv  Detail & Related papers  (2026-04-29T16:47:20Z)
• EviSearch: A Human in the Loop System for Extracting and Auditing Clinical Evidence for Systematic Reviews [7.325762712182949]
  EviSearch is a multi-agent extraction system for clinical evidence tables.<n>The pipeline is designed for high-precision extraction across multimodal evidence sources.<n>EviSearch is intended to accelerate living systematic review, reduce manual curation burden, and provide a safe, auditable path for integrating LLM-based extraction into evidence synthesis pipelines.
  arXiv  Detail & Related papers  (2026-03-23T22:36:54Z)
• Demo: Guide-RAG: Evidence-Driven Corpus Curation for Retrieval-Augmented Generation in Long COVID [3.716027375029187]
  We developed and evaluated six Retrieval-Augmented Generation (RAG) corpus configurations for Long COVID (LC) clinical question answering.<n>Our RAG corpus configuration combining clinical guidelines with high-quality systematic reviews consistently outperformed both narrow single-guideline approaches and large-scale literature databases.
  arXiv  Detail & Related papers  (2025-10-17T16:05:52Z)
• ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions [52.33835101586687]
  We study out-of-scope questions, where the retrieved document appears semantically similar to the question but lacks the necessary information to answer it.<n>We propose a guided hallucination-based approach ELOQ to automatically generate a diverse set of out-of-scope questions from post-cutoff documents.
  arXiv  Detail & Related papers  (2024-10-18T16:11:29Z)
• Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy [66.95501113584541]
  We propose an Iterative utiliTy judgm fraEntMework (ITEM) to promote each step in Retrieval-Augmented Generation (RAG)<n>RAG's three core components -- relevance ranking derived from retrieval models, utility judgments, and answer generation -- align with Schutz's philosophical system of relevances.<n> Experimental results demonstrate significant improvements of ITEM in utility judgments, ranking, and answer generation upon representative baselines.
  arXiv  Detail & Related papers  (2024-06-17T07:52:42Z)
• Self-supervised Answer Retrieval on Clinical Notes [68.87777592015402]
  We introduce CAPR, a rule-based self-supervision objective for training Transformer language models for domain-specific passage matching. We apply our objective in four Transformer-based architectures: Contextual Document Vectors, Bi-, Poly- and Cross-encoders. We report that CAPR outperforms strong baselines in the retrieval of domain-specific passages and effectively generalizes across rule-based and human-labeled passages.
  arXiv  Detail & Related papers  (2021-08-02T10:42:52Z)
• Learning Contextualized Document Representations for Healthcare Answer Retrieval [68.02029435111193]
  Contextual Discourse Vectors (CDV) is a distributed document representation for efficient answer retrieval from long documents. Our model leverages a dual encoder architecture with hierarchical LSTM layers and multi-task training to encode the position of clinical entities and aspects alongside the document discourse. We show that our generalized model significantly outperforms several state-of-the-art baselines for healthcare passage ranking.
  arXiv  Detail & Related papers  (2020-02-03T15:47:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.