EpiGraph creates a heterogeneous epilepsy knowledge graph that boosts LLM performance on clinical reasoning tasks by 30-41% in pharmacogenomics when used with Graph-RAG.
Diagnosisarena: Benchmarking diagnostic reasoning for large language models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Neural-MedBench reveals sharp performance drops in state-of-the-art VLMs on reasoning-intensive neurology tasks compared to conventional classification benchmarks, with reasoning failures dominating errors.
Creates the first bilingual clinical benchmark from Brazilian cases and reports that English performance advantage exists only in diagnosis retrieval, disappearing in the other three tasks.
EHRBench uses an EHR-LLM-KB pipeline to automatically create 960,067 reliable QA items spanning diagnosis, treatment, and prognosis for large-scale LLM evaluation in clinical decision making.
RareDxR1 is an LLM trained via knowledge internalization, reflection-enhanced sampling, and curriculum RL to perform open-domain rare disease diagnosis from raw notes without human-labeled phenotypes.
Dual-Stream Calibration uses entropy minimization and iterative meta-learning at test time to internalize clinical evidence and outperform standard in-context learning baselines on medical tasks.
MedXIAOHE is a medical MLLM that claims state-of-the-art benchmark performance through specialized pretraining to cover long-tail diseases and RL-based reasoning training.
citing papers explorer
-
EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild
EpiGraph creates a heterogeneous epilepsy knowledge graph that boosts LLM performance on clinical reasoning tasks by 30-41% in pharmacogenomics when used with Graph-RAG.
-
Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks
Neural-MedBench reveals sharp performance drops in state-of-the-art VLMs on reasoning-intensive neurology tasks compared to conventional classification benchmarks, with reasoning failures dominating errors.
-
Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese
Creates the first bilingual clinical benchmark from Brazilian cases and reports that English performance advantage exists only in diagnosis retrieval, disappearing in the other three tasks.
-
EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs
EHRBench uses an EHR-LLM-KB pipeline to automatically create 960,067 reliable QA items spanning diagnosis, treatment, and prognosis for large-scale LLM evaluation in clinical decision making.
-
RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotation
RareDxR1 is an LLM trained via knowledge internalization, reflection-enhanced sampling, and curriculum RL to perform open-domain rare disease diagnosis from raw notes without human-labeled phenotypes.
-
From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning
Dual-Stream Calibration uses entropy minimization and iterative meta-learning at test time to internalize clinical evidence and outperform standard in-context learning baselines on medical tasks.
-
MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
MedXIAOHE is a medical MLLM that claims state-of-the-art benchmark performance through specialized pretraining to cover long-tail diseases and RL-based reasoning training.