3 papers
cs.LG2026
Excess Description Length of Learning Generalizable Predictors
Elizabeth Donoway, Hailey Joren, Fabien Roger +1
Understanding whether fine-tuning elicits latent capabilities or teaches new ones is a fundamental question for language model evaluation and safety. We develop a formal informatio…
cs.CL2025
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Hailey Joren, Jianyi Zhang, Chun-Sung Ferng +3
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whet…
cs.LG2024
Classification with Conceptual Safeguards
Hailey Joren, Charles Marx, Berk Ustun
We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for mod…