STRIDE 解决了 LLM 训练数据归因计算成本高、依赖局部近似的痛点，做模型可解释性、数据质量分析的团队可以直接用这个新框架。
训练数据归因（TDA）旨在追溯模型预测与训练数据的关系，但传统方法依赖梯度追踪，对大型语言模型（LLM）计算成本极高。STRIDE 提出新思路：不在参数空间估计变化，而是在激活空间建模训练数据的功能影响。它通过轻量级“转向算子”模拟数据子集训练带来的行为偏移，并利用稀疏恢复技术从这些算子中分解出单个训练样本的影响。该方法在 LLM 预训练归因上达到最先进水平，且速度比此前方法快 13 倍。实验还验证了其在数据选择、数据污染检测等下游任务中的实用价值。
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 relies on local approximations. In this work, we propose a shift: rather than estimating parameter changes, we model the functional effect of training data in the activation space. We introduce STRIDE (Steering-based Training Data Influence Decomposition), a framework that formulates TDA as a sparse recovery problem in the spirit of compressive sensing. STRIDE learns lightweight "steering operators" that mimic the behavioral shift caused by training on data subsets. By measuring how these operators perturb test predictions, we recover individual training example influences via sparse linear decomposition. STRIDE achieves state-of-the-art for LLM pre-training attribution while being an order of magnitude ($13\times$) faster than previous art. We further validate its practical utility through downstream applications including data selection, data contamination, and qualitative analysis.