Assessing the Reliability of LLM-Generated Phenotype-Genotype Associations Through External Validation
Caiwan Sun, Yi Xin, Sarah Zeng, Sudeep D. Sunthankar, Wu-Chen Su, Jacob Lynn, Sergio Mundo, Mojgan Babanejad, QiPing Feng
The paper evaluates LLM-generated phenotype-genotype associations using external validation, finding 74.19% match genomic knowledge bases with varying support levels.
bioRxiv · Aug 21, 2026 · PreprintBioinformatics