Jundong Li
University of Virginia
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
When Safety Becomes An Outlier: Understanding the Retention of LLM Safety Behaviors
Researchers at the University of Virginia and Visa Research argue that language models lose safety training after fine-tuning because fixed refusal phrases are easy to learn and easy to overwrite. They propose training on natural, request-specific safety responses and report better retention.