3 papers
cs.HC2026
People Can Accurately Predict Behavior of Complex Algorithms That Are Available, Compact, and Aligned
Lindsay Popowski, Helena Vasconcelos, Ignacio Javier Fernandez +4
Users trust algorithms more when they can predict the algorithms' behavior. Simple algorithms trivially yield predictively accurate mental models, but modern AI algorithms have oft…
cs.AI2025
Rethinking Human Preference Evaluation of LLM Rationales
Ziang Li, Manasi Ganti, Zixian Ma +3
Large language models (LLMs) often generate natural language rationales -- free-form explanations that help improve performance on complex reasoning tasks and enhance interpretabil…
cs.LG2024
Clarify: Improving Model Robustness With Natural Language Corrections
Yoonho Lee, Michelle S. Lam, Helena Vasconcelos +2
The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data…