让下一篇重要论文，不再错过。

原文摘要

Large language models (LLMs) are often assumed to contain "safety regions” - parameter subsets whose modification directly influences safety behaviors. We conduct a systematic evaluation of four safety region identification methods spanning different parameter granularities, from individual weights to entire Transformer layers, across four families of backbone LLMs with varying sizes. Using ten safety identification datasets, we find that the identified safety regions exhibit only low to moderate overlap, as measured by IoU. The overlap drops significantly when the safety regions are further refined using utility datasets (i.e. non-harmful queries). These results suggest that current techniques fail to reliably identify a stable, dataset-agnostic safety region.