LLM Digest
Subscribe

Story

arxiv_cs_lg · Nov 12, 2026 · paper

Source brief

Sketching Language Models for Context Attribution

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

Continue reading

Read the original at arxiv.org →Open in live feedRead that day’s brief

Earlier in this thread 4 items