Encoding of pretrained large language models mirrors the genetic architectures of human psychological traits.
Xu, B.; Obradovich, N.; Zheng, W.; Loughnan, R.; Shao, L.; Misaki, M.; Thompson, W. K.; Paulus, M.; Fan, C. C.
Show abstract
Recent advances in large language models (LLMs) have prompted a frenzy in utilizing them as universal translators for biomedical terms. However, the black box nature of LLMs has forced researchers to rely on artificially designed benchmarks without understanding what exactly LLMs encode. We demonstrate that pretrained LLMs can already explain up to 51% of the genetic correlation between items from a psychometrically-validated neuroticism questionnaire, without any fine-tuning. For psychiatric diagnoses, we found disorder names aligned better with genetic relationships than diagnostic descriptions. Our results indicate the pretrained LLMs have encodings mirroring genetic architectures. These findings highlight LLMs potential for validating phenotypes, refining taxonomies, and integrating textual and genetic data in mental health research.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- GWAS of Over 427,000 Individuals Establishes GABAergic and Synaptic Molecular Pathways as Key for Cognitive Executive Functions 92%
- Computational phenotyping of aberrant belief updating in individuals with schizotypal traits and schizophrenia 92%
- Polygenic analyses show important differences between MDD symptoms collected using PHQ9 and CIDI-SF 91%
Similar papers in this journal
- Polygenic risk scores lack prognostic value for adults with severe mental illness 93%
- Identification of 64 new risk loci for major depression, refinement of the genetic architecture and risk prediction of recurrence and comorbidities 91%
- Multi-ancestry study of the genetics of problematic alcohol use in >1 million individuals 91%
Similar papers in this journal
- Clinical Knowledge Extraction via Sparse Embedding Regression (KESER) with Multi-Center Large Scale Electronic Health Record Data 91%
- Continuous-Time and Dynamic Suicide Attempt Risk Prediction with Neural Ordinary Differential Equations 91%
- Personalized Mood Prediction from Patterns of Behavior Collected with Smartphones 91%
Similar papers in this journal
- Multivariate GWAS of psychiatric disorders and their cardinal symptoms reveal two dimensions of cross-cutting genetic liabilities 93%
- Effects of gene dosage on cognitive ability: A function-based association study across brain and non-brain processes 90%
- Variant-resolved prediction of context-specific isoform variation with a graph-based attention model 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.