Showing 2026Show all
2 papers · 1 filter
cs.CL2026
ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models
Sahil Kale, Ian Harris
Large Language Models (LLMs) often require selective removal of harmful or sensitive knowledge, called unlearning, yet existing benchmarks evaluate this capability incompletely. Th…
cs.LG2026
Memisis: Orchestrating and Evaluating Synthetic Data for Tabular Health Datasets
Nitish Nagesh, Pengbao Zhou, Atchuth Naveen Chilaparasetti +8
Synthetic data is widely used in healthcare to create datasets that preserve statistical properties of real data without exposing sensitive patient information. Generating and eval…