2 papers
cs.CL2025
Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions
Eve Fleisig, Matthias Orlikowski, Philipp Cimiano +1
For machine learning datasets to accurately represent diverse opinions in a population, they must preserve variation in data labels while filtering out spam or low-quality response…
cs.CL2025
Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions
Matthias Orlikowski, Jiaxin Pei, Paul Röttger +3
People naturally vary in their annotations for subjective questions and some of this variation is thought to be due to the person's sociodemographic characteristics. LLMs have also…