2 papers
cs.CY2025
Rethinking LLM Bias Probing Using Lessons from the Social Sciences
Kirsten N. Morehouse, Siddharth Swaroop, Weiwei Pan
The proliferation of LLM bias probes introduces three significant challenges: (1) we lack principled criteria for choosing appropriate probes, (2) we lack a system for reconciling…
cs.LG2023
Discovering User Types: Mapping User Traits by Task-Specific Behaviors in Reinforcement Learning
L. L. Ankile, B. S. Ham, K. Mao +4
When assisting human users in reinforcement learning (RL), we can represent users as RL agents and study key parameters, called \emph{user traits}, to inform intervention design. W…