2 papers
cs.AI2026
Estimating Uncertainty in Classifier Performance with Applications to Large Language Models and Nested Data
Kylie Anglin
Researchers increasingly use text classification--supervised models or large language models--to measure constructs from natural language, providing metrics such as recall and prec…
cs.CL2026
Empirical Prompt Engineering for Construct Identification with Large Language Models
Kylie L. Anglin, Stephanie Milan, Brittney Hernandez +1
Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong performance on text classification tasks. However, LLM classifications are hig…