← Back to the feed
AI & softwareResearch findings

A Sketching Method for Context Attribution in Language Models

Original published 2026.11.13 03:57 KSTAdded to Blackdeck 2026.11.14 18:17 KST

What has changed?

A sketching method reduces evaluation calls for context attribution by leveraging stability assumptions and backpropagation circuit differentiation

Key points

  1. Context attribution analyzes how removing prompt parts affects language model outputs.
  2. Traditional leave-one-out methods require n model evaluations, which is computationally expensive.
  3. Proposed sketching method reduces evaluation calls to O(√(log(1/ε)/ε)) under stability assumption

Connect it to your work

The method achieves error proportional to ε with O(√(log(1/ε)/ε)) model evaluations under stability assumption

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivSketching Language Models for Context Attribution