Story
arxiv_cs_lg · Nov 12, 2026 · paper
arxiv.orgNov 12, 2026
original source linked
In brief
Context attribution asks how removing parts of a prompt changes a language model's output. We study leave-one-out (LOO) attribution for a prompt of $n$ tokens and a fixed measurement function. Computing all LOO values directly requires $n$ model evaluations. Under a stability ass