Poster
in
Workshop: GenAI for Health: Potential, Trust and Policy Compliance
Contextual evaluation of Large Language Models for Classifying Tropical and Infectious Diseases
Mercy Asiedu · Nenad Tomasev · Chintan Ghate · Tiya Tiyasirichokchai · Awa Dieng · Oluwatosin Akande · Geoffrey Siwo · Steve Adudans · Sylvanus Aitkins · Odianosen Ehiakhamen · Eric Ndombi · Katherine Heller
Keywords: [ large language models ] [ Tropical and infectious diseases ] [ global health ] [ health equity ] [ red teaming ]
While large language models (LLMs) have shown promise for medical question answering, there is limited work focused on tropical and infectious disease-specific exploration. We build on an opensource tropical and infectious diseases (TRINDs) dataset, expanding it to include demographic and semantic clinical and consumer augmentations yielding 11000+ prompts. We evaluate LLM performance on these, comparing generalist and medical LLMs, as well as LLM outcomes to human experts. We demonstrate through systematic experimentation, the benefit of contextual information such as demographics, location, gender, risk factors for optimal LLM response. Finally we develop a prototype of TRINDs-LM, a research tool that provides a playground to navigate how context impacts LLM outputs for health.