Sketching Language Models for Context Attribution
cs.DS, cs.AI, cs.LG, stat.ML
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Fixed-sparsity matrix approximation from matrix-vector products
- Data Attribution via Sketched Metadifferentiation
- How to sketch a learning algorithm
- MAGIC: Near-Optimal Data Attribution for Deep Learning
- Understanding Neural Networks through Representation Erasure
- Finite-sample properties of the trimmed mean
- Tight Query Complexity Lower Bounds for PCA via Finite Sample Deformed Wigner Law
Related papers
- Exploiting Low Scanwidth to Resolve Soft Polytomies
- PHastR: Faster Minimal Perfect Hashing with Rotated Layouts
- Fine-Grained Complexity of Approximating Vector Knapsack: A Faster Algorithm and Equivalence with k-SUM in 2D
- Polynomial-time computation of p-contraction fixed points for even p
- Separations Between Submodular-Like Graph Widths
- Bounded Integer Programming in Almost N 2d Time