10 citations · 45 across the 25 of their papers we have counts for
17 papers · 1 filter
How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines
Junwei Deng, Pingbang Hu, Suliang Jin +4
Trajectory-based data attribution methods estimate the influence of training samples on model predictions by unrolling the training trajectory. They are widely used in applications…
A Sustainable AI Economy Needs Data Deals That Work for Generators
Ruoxi Jia, Luis Oala, Wenjie Xiong +4
We argue that the machine learning value chain is structurally unsustainable due to an economic data processing inequality: each state in the data cycle from inputs to model weight…
Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
Jiachen T. Wang, Tong Wu, Kaifeng Lyu +4
Data teams at frontier AI companies routinely train small proxy models to make critical decisions about pretraining data recipes for full-scale training runs. However, the communit…
Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
Mahavir Dabas, Tran Huynh, Nikhil Reddy Billa +8
Large language models remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Defending against novel jailbreaks represents a critical chall…
Effectively Controlling Reasoning Models through Thinking Intervention
Tong Wu, Chong Xiang, Jiachen T. Wang +2
Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solvi…
Capturing the Temporal Dependence of Training Data Influence
Jiachen T. Wang, Dawn Song, James Zou +2
Traditional data influence estimation methods, like influence function, assume that learning algorithms are permutation-invariant with respect to training data. However, modern tra…
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
Myeongseob Ko, Henry Li, Zhun Wang +6
Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful o…
Data Shapley in One Training Run
Jiachen T. Wang, Prateek Mittal, Dawn Song +1
Data Shapley provides a principled framework for attributing data's contribution within machine learning contexts. However, existing approaches require re-training models on differ…
Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits
Jiachen T. Wang, Tianji Yang, James Zou +2
Data Shapley provides a principled approach to data valuation and plays a crucial role in data-centric machine learning (ML) research. Data selection is considered a standard appli…
An Economic Solution to Copyright Challenges of Generative AI
Jiachen T. Wang, Zhun Deng, Hiroaki Chiba-Okabe +2
Generative artificial intelligence (AI) systems are trained on large data corpora to generate new pieces of text, images, videos, and other media. There is growing concern that suc…
Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation
Jiachen T. Wang, Yuqing Zhu, Yu-Xiang Wang +2
Data valuation aims to quantify the usefulness of individual data sources in training machine learning (ML) models, and is a critical aspect of data-centric ML research. However, d…
Privacy-Preserving In-Context Learning for Large Language Models
Tong Wu, Ashwinee Panda, Jiachen T. Wang +1
In-context learning (ICL) is an important capability of Large Language Models (LLMs), enabling these models to dynamically adapt based on specific, in-context exemplars, thereby im…
LAVA: Data Valuation without Pre-Specified Learning Algorithms
Hoang Anh Just, Feiyang Kang, Jiachen T. Wang +4
Traditionally, data valuation (DV) is posed as a problem of equitably splitting the validation performance of a learning algorithm among the training data. As a result, the calcula…
Uncovering Adversarial Risks of Test-Time Adaptation
Tong Wu, Feiran Jia, Xiangyu Qi +4
Recently, test-time adaptation (TTA) has been proposed as a promising solution for addressing distribution shifts. It allows a base model to adapt to an unforeseen distribution dur…
Data Banzhaf: A Robust Data Valuation Framework for Machine Learning
Jiachen T. Wang, Ruoxi Jia
Data valuation has wide use cases in machine learning, including improving data quality and creating economic incentives for data sharing. This paper studies the robustness of data…
Towards A Proactive ML Approach for Detecting Backdoor Poison Samples
Xiangyu Qi, Tinghao Xie, Jiachen T. Wang +3
Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison sample…
ModelPred: A Framework for Predicting Trained Model from Training Data
Yingyan Zeng, Jiachen T. Wang, Si Chen +3
In this work, we propose ModelPred, a framework that helps to understand the impact of changes in training data on a trained model. This is critical for building trust in various s…