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

ArXi:2605.16591v1 Announce Type: new 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-level sub-FVs, suggesting additive and composable contributions from individual nstrations.