1
Jacobian Scopes: token-level causal attributions in LLMs
提出 Jacobian Scopes 方法,实现大语言模型 token 级因果归因,论文已更新至 v3。
arXiv:2601.16407v3 Announce Type: replace-cross Abstract: Large language models (LLMs) make next-token predictions based on clues present in their con…