Llama-2-7B

Zhipu AI released GLM-5.3, a controlled experiment showing that scaling post-training with RL for one month, while keeping base architecture and parameters identical to GLM-5.2, yields significant cap…

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'…