Picture for Yahan Yang

Yahan Yang

Benchmarking LLM Guardrails in Handling Multilingual Toxicity

Add code
Oct 29, 2024
Viaarxiv icon

Understanding Calibration for Multilingual Question Answering Models

Add code
Nov 15, 2023
Viaarxiv icon

Using Semantic Information for Defining and Detecting OOD Inputs

Add code
Feb 21, 2023
Viaarxiv icon

In and Out-of-Domain Text Adversarial Robustness via Label Smoothing

Add code
Dec 20, 2022
Viaarxiv icon

Memory Classifiers: Two-stage Classification for Robustness in Machine Learning

Add code
Jun 10, 2022
Figure 1 for Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
Figure 2 for Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
Figure 3 for Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
Figure 4 for Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
Viaarxiv icon