Search Results for author:
Found 7 papers, 0 papers with code
Better Think with Tables: Leveraging Tables to Enhance Large Language Model Comprehension
Despite the recent advancement of Large Langauge Models (LLMs), they struggle with complex queries often involving multiple conditions, common in real-world scenarios.
PFGuard: A Generative Framework with Privacy and Fairness Safeguards
Generative models must ensure both privacy and fairness for Trustworthy AI.
Personalized DP-SGD using Sampling Mechanisms
Personalized privacy becomes critical in deep learning for Trustworthy AI.
Redactor: A Data-centric and Individualized Defense Against Inference Attacks
Our experiments show that a probabilistic decision boundary can be a good proxy for labelers, and that our approach is effective in defending against inference attacks and can scale to large data.
Responsible AI Challenges in End-to-end Machine Learning
Second, responsible AI must be broadly supported, preferably in all steps of machine learning.
Inspector Gadget: A Data Programming-based Labeling System for Industrial Images
We propose Inspector Gadget, an image labeling system that combines crowdsourcing, data augmentation, and data programming to produce weak labels at scale for image classification.
A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspective
Interestingly, recent research in data collection comes not only from the machine learning, natural language, and computer vision communities, but also from the data management community due to the importance of handling large amounts of data.
