1 citations · 1 across the 7 of their papers we have counts for
7 papers
How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation
Eduardo Tenorio, Karuna Bhaila, Xintao Wu
Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a princip…
Cross-Modal Attention Guided Unlearning in Vision-Language Models
Karuna Bhaila, Aneesh Komanduri, Minh-Hao Van +1
Vision-Language Models (VLMs) have demonstrated immense capabilities in multi-modal understanding and inference tasks such as Visual Question Answering (VQA), which requires models…
CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models
Aneesh Komanduri, Karuna Bhaila, Xintao Wu
Large language models (LLMs) have shown remarkable ability in various language tasks, especially with their emergent in-context learning capability. Extending LLMs to incorporate v…
Fair In-Context Learning via Latent Concept Variables
Karuna Bhaila, Minh-Hao Van, Kennedy Edemacu +3
The emerging in-context learning (ICL) ability of large language models (LLMs) has prompted their use for predictive tasks in various domains with different data types, including t…
Soft Prompting for Unlearning in Large Language Models
Karuna Bhaila, Minh-Hao Van, Xintao Wu
The widespread popularity of Large Language Models (LLMs), partly due to their unique ability to perform in-context learning, has also brought to light the importance of ethical an…
DP-TabICL: In-Context Learning with Differentially Private Tabular Data
Alycia N. Carey, Karuna Bhaila, Kennedy Edemacu +1
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks by conditioning on demonstrations of question-answer pairs and it has been shown to have compar…
Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach
Karuna Bhaila, Wen Huang, Yongkai Wu +1
Graph Neural Networks have achieved tremendous success in modeling complex graph data in a variety of applications. However, there are limited studies investigating privacy protect…