Article

Frequency-Stratified Benchmarking Reveals Strong Long-Tail Limitations of Large Language Models in Diagnosis of Monogenic Diseases

2026-06-29

Abstract excerpt

<title>Abstract</title> <p>Knowledge of monogenic disorders is long-tailed: a small number of canonical disease genes are extensively represented in the literature, whereas many rare, recently characterized genes remain sparsely reported. What remains less clearly characterized is how this uneven knowledge structure affects the diagnostic behavior of large language models (LLMs). Here we present MendelianBench-5K...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: bd1f4264-dede-5dc7-96c3-75f295b170da
DOI: 10.21203/rs.3.rs-10158732/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Frequency-Stratified Benchmarking Reveals Strong Long-Tail Limitations of Large Language Models in Diagnosis of Monogenic DiseasesDOI 10.21203/rs.3.rs-10158732/v1Read

Genetic Transformer: An Innovative Large Language Model Driven Approach for Rapid and Accurate Identification of Causative Variants in Rare Genetic DiseasesSemantic proximity Read

Large Language Model as a Promising Framework for the Complete Clinical Interpretation of Human Genetic VariantsSemantic proximity Read

Large Language Models Enhance Molecular Diagnoses of Mendelian Disorders via A Novel LogicSemantic proximity Read

Language models reveal evidence gaps in variants of uncertain significanceSemantic proximity Read

Variant Classification Using Proteomics-Informed Large Language Models Increases Power of Rare Variant Association Studies and Enhances Target Discovery.Semantic proximity Read

Variant Classification Using Proteomics-Informed Large Language Models Increases Power of Rare Variant Association Studies and Enhances Target DiscoverySemantic proximity Read

Reframing AI for Rare Disease RecognitionSemantic proximity Read

Discovering Monogenic Patients with a Confirmed Molecular Diagnosis in Millions of Clinical Notes with MonoMinerSemantic proximity Read

A systematic review and meta-analysis of the Diagnostic Performance of Large Language Models in Rare DiseasesSemantic proximity Read

eRAM: encyclopedia of rare disease annotations for precision medicine.Semantic proximity Read

GEN-KnowRD: Reframing AI for Rare Disease RecognitionSemantic proximity Read

Assessing the utility of large language models for phenotype-driven gene prioritization in the diagnosis of rare genetic disease.Semantic proximity Read