The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning
On the map: LLM reasoning → Clinical and biomedical applications
Abstract (arXiv)
Frontier large language models generate clinically accurate outputs, but their citations are often fabricated. We term this the Provenance Gap. We tested five frontier LLMs across 36 clinician-validated scenarios for three rare neuromuscular disease pairs. No model produced a clinically relevant PubMed identifier without prompting. When explicitly asked to cite, the best model achieved 15.3% relevant PMIDs; the majority resolved to real publications in unrelated fields. We present HEG-TKG (Hierarchical Evidence-Grounded Temporal Knowledge Graphs), a system that grounds clinical claims in temporal knowledge graphs built from 4,512 PubMed records and curated sources with quality-tier stratification and 1,280 disease-trajectory milestones. In a controlled three-arm comparison using the same synthesis model, HEG-TKG matches baseline clinical feature coverage while achieving 100% evidence verifiability with 203 inline citations. Guideline-RAG, given overlapping source documents as raw text, produces zero verifiable citations. LLM judges cannot distinguish fabricated from verified citations without PubMed audit data. Independent clinician evaluation confirms the verifiability advantage (Cohen's d = 1.81, p < 0.001) with no degradation on safety or completeness. A counterfactual experiment shows 80% resistance to injected clinical errors with 100% detectability via citation trace. The system deploys on-premise via open-source models so patient data never leaves institutional infrastructure.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 14 of its 61 references that are in the map. First posted on arXiv 18 Apr 2026.
Builds on
14 of 61 references.
References · 14
- 2023GPT-4 Technical Reportcited by 18,396
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2024Qwen2.5 Technical Reportcited by 4,942
- 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
- 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
- 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
- 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 872
- 2024DeepSeek-V3 Technical Reportcited by 811
- 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
- 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 638
- 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 384
- 2019ScispaCy: Fast and Robust Models for Biomedical Natural Language Processingcited by 244
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases
- 2026Clinical Reasoning Graphs: Structured Evaluation of LLM Diagnostic Reasoning Reveals Competence Without Consistency
- 2026Clinical Knowledge Graph Construction and Evaluation with Multi-LLMs via Retrieval-Augmented Generation
- 2026Building evidence-based knowledge bases from full-text literature for disease-specific biomedical reasoning
- 2025Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine
- 2026MMRareBench: A Rare-Disease Multimodal and Multi-Image Medical Benchmark
- 2026Training-Free Clinical Reasoning through Medical Ontologies and Cognitive Mapping: A Symbolic-Probabilistic Knowledge Graph Framework
- 2026MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation