AI Research

STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations

Medium Severity Global
Date Occurred Jun 03, 2026 17:59 UTC
Event Type AI Research
Source arXiv
Recorded Jun 04, 2026
Full Description

arXiv: STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The gold standard for TDA relies on causal interventions, observing how a model changes when data is added or removed, but repeated retraining is computationally challenging for Large Language Models (LLMs). Consequently, most approaches approximate this effect in the parameter space using gradients. However, tracking gradients across billions of parameters is not only prohibitively expensive but reli

AI Intelligence Layer

AI Categories

application
Event Metadata
  • ID #5844
  • Type AI Research
  • Region Global
  • Severity Medium
  • Indexed Jun 04, 2026