arXiv:2509.24319v4 Announce Type: replace-cross Abstract: Large language models can express values in two main ways: (1) intrinsic expression, reflecting the model's inherent values learned during training, and (2) prompted expression, elicited by explicit prompts. Given their widespread use in value alignment, it is paramount to clearly understand their underlying mechanisms, particularly whether they mostly overlap (as one might expect) or rely on distinct mechanisms. We analyze this largely understudied problem at the mechanistic level using two approaches: (1) value vectors, feature direct
Source: arXiv cs.AI — read the full report at the original publisher.