2 papers
cs.CL2026
From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models
Kyle Richardson, Cullen Anderson, Pranav Balakrishnan +4
While Large Language Models have improved rapidly, many fundamental questions remain about how to evaluate the knowledge and reasoning abilities they acquire, and how such evaluati…
cs.CL2025
Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning
Anh Pham, Mihir Thalanki, Michael Sun +6
Large language models often lose previously aligned safety behaviors when fine-tuned on benign data, a phenomenon known as catastrophic forgetting. Prior work shows that adding ran…