Showing 2025Show all
3 papers · 1 filter
cs.AI2025
Position: AI Evaluations Should be Grounded on a Theory of Capability
Nathanael Jo, Ashia Wilson
Evaluations of generative models are now ubiquitous, and their outcomes critically shape public and scientific expectations of AI's capabilities. Yet skepticism about their reliabi…
cs.CL2025
UCD: Unlearning in LLMs via Contrastive Decoding
Vinith M. Suriyakumar, Ayush Sekhari, Ashia Wilson
Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an…
cs.LG2025
Layered Unlearning for Adversarial Relearning
Timothy Qian, Vinith Suriyakumar, Ashia Wilson +1
Our goal is to understand how post-training methods, such as fine-tuning, alignment, and unlearning, modify language model behavior and representations. We are particularly interes…