Authors

Shixuan Liu

Publications 2

Preprint Open access

dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale

Shixuan Liu, Tongli Zhou, Junwei Deng et al. · 2026

Training data attribution (TDA) estimates the contribution of individual training examples to model outputs. Most scalable TDA methods rely on per-example gradients, whose computation and use at LLM scale pose challenges in efficiency, compatibility, and extensibility. We introduce dattri-LLM, a TDA library that makes …

Preprint Open access

Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution

Shixuan Liu, Joan Serrà, Kin Wai Cheuk et al. · 2026

Training data attribution for diffusion models aims to identify the training samples that influence a generated instance, but existing methods either require costly per-sample gradient computation or query-specific model optimization. Moreover, most methods attribute changes in a proxy loss rather than changes in the a …

Co-authors