Search Results for author:
Found 6 papers, 3 papers with code
Representation Bending for Large Language Model Safety
Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges.
Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
Auditing Differentially Private Stochastic Gradient Descent (DP-SGD) in the final model setting is challenging and often results in empirical lower bounds that are significantly looser than theoretical privacy guarantees.
Large Language Models Still Exhibit Bias in Long Text
Existing fairness benchmarks for large language models (LLMs) primarily focus on simple tasks, such as multiple-choice questions, overlooking biases that may arise in more complex scenarios like long-text generation.
ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments
To bridge the gap between these learning environments and deploying (i. e., real) environments, we propose the ReALFRED benchmark that employs real-world scenes, objects, and room layouts to learn agents to complete household tasks by understanding free-form language instructions and interacting with objects in large, multi-room and 3D-captured scenes.
An Information Theoretic Evaluation Metric For Strong Unlearning
Machine unlearning (MU) aims to remove the influence of specific data from trained models, addressing privacy concerns and ensuring compliance with regulations such as the "right to be forgotten."
Learning Equi-angular Representations for Online Continual Learning
Online continual learning suffers from an underfitted solution due to insufficient training for prompt model update (e. g., single-epoch training).
