New paper about LLM Unlearning Benchmark(parametric-based)

[yihuaihong]

The new paper about LLM Unlearning Benchmark (parametric-based) Arxiv: arxiv.org/abs/2406.11614 Website: https://yihuaihong.github.io/ConceptVectors.github.io/ Github: https://github.com/yihuaihong/ConceptVectors