A new arXiv study (2608.21606v1) finds that large language models (LLMs) can still recover supposedly 'forgotten' information through adversarial prompting, with attack success rates (ASR) between 72.…
A new study reveals that LUNAR, a state-of-the-art LLM unlearning method, fails to truly remove knowledge, as two attack routes can recover "forgotten" information. The author demonstrates that LUNAR'…
A two-week project by a BlueDot Project cohort participant found that standard post-training compression processes (quantization, magnitude pruning, SVD truncation) minimally reverse unlearning on the…
Researchers have introduced BalDRO, a novel framework for balanced unlearning in large language models that addresses asynchronous forgetting by focusing on hard-to-unlearn data distributions. BalDRO,…