Select or Project? Evaluating Lower-dimensional Vectors for LLM Training Data Explanations

arXiv:2601.16651v3 Announce Type: replace Abstract: Gradient-based methods for instance-based explanation for large language models (LLMs) are hindered by the immense dimensionality of model gradients. In practice, influence estimation is restricted to a subset of model parameters to make computation tractable, but this subset is often chosen ad hoc and rarely justified by systematic evaluation. This paper investigates if it is better to create low-dimensional representations by selecting a small, architecturally informed subset of model components or by projecting the full gradients into a lower-dimensional space. Using a novel benchmark, we show that a greedily selected subset of components captures the information about training data influence needed for a retrieval task more effectively than either the full gradient or random projection. We further find that this approach is more computationally efficient than random projection, demonstrating that targeted component selection is a practical strategy for making instance-based explanations of large models more computationally feasible.

Related

• From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models
• Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
• Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!

Source: arXiv cs.CL | 2026-07-31