Propagating construction-time knowledge quality into medical question answering: A framework grounded in clinical guidelines

• URL: http://arxiv.org/abs/2608.28360v1
• Date: Fri, 28 Aug 2026 14:11:20 GMT
• Title: Propagating construction-time knowledge quality into medical question answering: A framework grounded in clinical guidelines
• Abstract summary: We investigate whether construction-time triple quality can serve as a persistent signal for downstream evidence selection and presentation.<n>We propose a quality-aware framework that models structural (Conf) and evidential support (EvidScore) as complementary dimensions and fuses them into a per-triple quality signal, Q(t)<n> Experiments on Chinese diabetes clinical guidelines show that the utility of the quality signal is distribution dependent.
• Score: 19.37240845977001
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models have facilitated knowledge graph (KG) construction from clinical guidelines, but extracted triples vary in structural validity and evidential support. Meanwhile, graph-augmented question answering (QA) systems typically optimize query relevance during retrieval, with limited reuse of quality information produced during KG construction. This creates a disconnect between construction-time quality control and inference-time evidence use. We investigate whether construction-time triple quality can serve as a persistent signal for downstream evidence selection and presentation. We propose a quality-aware framework that models structural conformance (SchemaConf) and evidential support (EvidScore) as complementary dimensions and fuses them into a per-triple quality signal, Q(t). Rather than using quality solely for filtering, the framework retains Q(t) and derived quality tiers as graph attributes and propagates them into quality-weighted subgraph retrieval and tier-conditioned evidence prompting, while preserving passage-level provenance. Experiments on Chinese diabetes clinical guidelines show that the utility of the quality signal is distribution dependent. Under cross-version and cross-model shift, the fused Q(t) provides stronger triple-quality discrimination than either component alone (AUC 0.748 vs. 0.703 for EvidScore and 0.645 for SchemaConf). In guideline-grounded QA, propagating construction-time quality reduces required-knowledge omission from 16.3% to 5.3% and conflicting outputs from 16.3% to 2.7%, with an evidence-grounded precision of 81.6% and near-zero invalid citations. Blinded clinician ratings favor the full framework over no retrieval (4.68 vs. 4.21 on a five-point scale) and approach the oracle condition (4.80), while cross-generator experiments show consistent trends.

Related papers

• Graph-Supervised Hierarchical Clinical Alignment for Radiology Report Generation with Large Language Models [46.202482780666635]
  Graph-Hierarchicald Supervised Clinical Alignment reformulates image-report supervision as a hierarchical clinical alignment problem.<n>Our method structures this alignment as a disease-conditioned process, where supervision is decomposed into two levels.<n> Experiments on MIMIC-CXR, IU-Xray, and COV-CTR show that our method consistently improves performance on both conventional and clinical metrics.
  arXiv  Detail & Related papers  (2026-08-25T06:32:26Z)
• HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research [52.87128503345243]
  We introduce HiEviDR-Bench, a benchmark for evaluating Hierarchical Evidence Aggregation in Deep Research.<n>HiEviDR-Bench represents each instance with an explicit evidence graph that captures evidence selection, cross-source linking, and aggregation.<n>We develop a traceability-oriented evaluation framework with five dimensions: report quality, evidence traceability, citation accuracy, claim verification, and answer correctness.
  arXiv  Detail & Related papers  (2026-07-27T23:50:46Z)
• PointQ-Bench: Benchmarking Diagnostic and Interpretable Point Cloud Quality Assessment [28.88904276309088]
  Point cloud quality plays a critical role in 3D acquisition, reconstruction, rendering, and perception.<n>We introduce PointQ-Bench, a benchmark designed to extend PCQA from scalar scoring toward comprehensive quality understanding.<n>PointQ-Bench consists of 3,083 point clouds spanning authentic scans, simulated distortions, and AI-generated content, covering eight major issue types.
  arXiv  Detail & Related papers  (2026-05-27T09:56:36Z)
• ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning [49.05361955143476]
  ClinSeekAgent is an automated agentic framework for dynamic multimodal evidence seeking.<n>Given only a clinical query and access to raw data sources, ClinSeekAgent gathers evidence by querying medical knowledge bases, navigating raw EHRs, and invoking medical imaging tools.
  arXiv  Detail & Related papers  (2026-05-19T17:58:37Z)
• Automating Clinical Information Retrieval from Finnish Electronic Health Records Using Large Language Models [0.0]
  Locally deployable framework answers clinical questions directly from EHRs without external data transfer.<n>Open-source large language models (LLMs) ranging from 4B to 70B parameters were benchmarked under fully offline conditions.
  arXiv  Detail & Related papers  (2026-03-27T14:03:51Z)
• Quantized Vision-Language Models for Damage Assessment: A Comparative Study of LLaVA-1.5-7B Quantization Levels [0.0]
  This paper presents a comprehensive study of quantized Vision-Language Models (VLMs) for automated bridge damage assessment.<n>We focus on the trade-offs between description quality, inference speed, and resource requirements.<n>We develop an end-to-end pipeline combining LLaVA-1.5-7B for visual damage analysis, structured extraction, and rule-based priority scoring.
  arXiv  Detail & Related papers  (2026-03-24T12:33:18Z)
• A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice [83.11942224668127]
  Janus-Pro-CXR (1B) is a chest X-ray interpretation system based on DeepSeek Janus-Pro model.<n>Our system outperforms state-of-the-art X-ray report generation models in automated report generation.
  arXiv  Detail & Related papers  (2025-12-23T13:26:13Z)
• CONFIDE: Hallucination Assessment for Reliable Biomolecular Structure Prediction and Design [46.12506067241116]
  We present CODE (Chain of Diffusion Embeddings), a self evaluating metric to quantify topological frustration.<n>We propose CONFIDE, a unified evaluation framework that combines energetic and topological perspectives.<n>By combining data driven embeddings with theoretical insight, CODE and CONFIDE outperform existing metrics across a wide range of biomolecular systems.
  arXiv  Detail & Related papers  (2025-11-20T03:38:46Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• Evaluating Large Language Models for Evidence-Based Clinical Question Answering [4.101088122511548]
  Large Language Models (LLMs) have demonstrated substantial progress in biomedical and clinical applications.<n>We curate a benchmark drawing from Cochrane systematic reviews and clinical guidelines.<n>We observe consistent performance patterns across sources and clinical domains.
  arXiv  Detail & Related papers  (2025-09-13T15:03:34Z)
• Quality Sentinel: Estimating Label Quality and Errors in Medical Segmentation Datasets [11.134987228105162]
  We introduce a regression model, Quality Sentinel, to estimate label quality compared with manual annotations in medical segmentation datasets. This regression model was trained on over 4 million image-label pairs created by us. Our Quality Sentinel can predict the label quality of 142 body structures.
  arXiv  Detail & Related papers  (2024-06-01T07:03:15Z)

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.