7 papers
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
Yuzheng Hu, Ryan McKenna, Da Yu +4
Generating high-quality synthetic text under differential privacy (DP) is critical for training and evaluating language models without compromising user privacy. Prior work on synt…
GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection
Pingbang Hu, Joseph Melkonian, Weijing Tang +2
Gradient-based data attribution methods, such as influence functions, are critical for understanding the impact of individual training samples without requiring repeated model retr…
DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
Cathy Jiao, Yijun Pan, Emily Xiao +6
Data attribution methods quantify the influence of training data on model outputs and are becoming increasingly relevant for a wide range of LLM research and applications, includin…
Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
Weiyi Wang, Junwei Deng, Yuzheng Hu +5
Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric application…
MergeBench: A Benchmark for Merging Domain-Specialized LLMs
Yifei He, Siqi Zeng, Yuzheng Hu +3
Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without t…
A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
Yuzheng Hu, Fan Wu, Haotian Ye +5
Online reinforcement learning (RL) excels in complex, safety-critical domains but suffers from sample inefficiency, training instability, and limited interpretability. Data attribu…