Target Population
Target population research focuses on accurately defining and modeling the characteristics of a specific group for various applications, from material science to healthcare and social sciences. Current research employs diverse approaches, including large language models (LLMs) for predicting user stances and preferences, optimization algorithms for identifying underrepresented subgroups within trial populations, and novel machine learning architectures for improving the generalizability of inferences from studies. This work is crucial for enhancing the reliability and applicability of scientific findings and improving the effectiveness of interventions across diverse fields, ultimately leading to more accurate predictions and more equitable outcomes.
Papers
A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language
Nikita Kartashov, Nikolaos N. Vlassis
Predicting User Stances from Target-Agnostic Information using Large Language Models
Siyuan Brandon Loh, Liang Ze Wong, Prasanta Bhattacharya, Joseph Simons, Wei Gao, Hong Zhang