[2605.11143] ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
[Submitted on 11 May 2026]
Title:ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
View a PDF of the paper titled ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV, by Alex Stinard
View PDF HTML (experimental)
Abstract:Reasoning benchmarks measure clinical performance on clean inputs. We evaluate the step before reasoning: retrieval over real EHR notes, where negation, temporality, and family-versus-patient attribution can flip a correct answer to a wrong one. EpiKG carries an assertion label and a temporality tag with every fact in a patient knowledge graph, then routes retrieval by question intent. ClinicalBench is a 400-question test over 43 MIMIC-IV patients across 9 assertion-sensitive categories. A 7-condition ablation tests each piece of EpiKG across six LLMs (Claude Opus 4.6, GPT-OSS 20B, MedGemma 27B, Gemma 4 31B, MedGemma 1.5 4B, Qwen 3.5 35B). Three physicians blindly adjudicated 100 paired items. The author-blind primary endpoint, leave-author-out paired exact McNemar on 50 unanimous-strict items rated by two external physicians, yields +22.0 percentage points (95 percent Newcombe CI [+5.1, +31.5], p=0.0192). The architectural novelty, intent-aware KG-RAG over a Contriever dense-RAG baseline (C2b to C4g_kw on the change-excluded n=362 endpoint), is +8.84 percentage points (paired McNemar p=1.79e-3); +12.43 percentage points under oracle intent. Sensitivities agree directionally: three-rater physician majority +24.0 percentage points (subject to single-author circularity); deterministic keyword reproducibility proxy +39.5 percentage points. Across the six models, the gain shrinks as the LLM-alone baseline rises (beta=-1.123, r=-0.921, p=0.009). With n=6 this looks more like regression to the mean than encoding substituting for model size. Physician adjudication identified 56 percent of auto-generated reference answers as defective, a methodological finding indicating that NLP-pipeline clinical-QA benchmarks require physician adjudication to be usable. ClinicalBench, the frozen evaluator, three-rater adjudication data, and the EpiKG output stack are publicly released.
Comments: 46 pages including appendices (two-column preprint format). Under review at JAMIA. Code, frozen evaluator, and benchmark released at this https URL. ClinicalBench v2 is a 400-question MIMIC-IV stress test for assertion-aware retrieval
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
Cite as: arXiv:2605.11143 [cs.CL]
(or arXiv:2605.11143v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.11143
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Alex Stinard [view email] [v1] Mon, 11 May 2026 18:47:52 UTC (296 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV, by Alex Stinard
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs cs.AI cs.IR
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)