How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning 事件

How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning arXiv:2605.16591v2 Announce Type: replace-cross Abstract: In-context learning (ICL) excels at new tasks from minimal examples, yet we still lack a mechanistic explanation of how few-shot prompts shape a model's function vector (FV)--a causal activation direction that drives task behavior on the ICL query. Across tasks and models, an $n$-shot FV is well-approximated by a linear combination of example-