Search Results for author:
Found 5 papers, 0 papers with code
On the Calibration of Multilingual Question Answering LLMs
We also conduct several ablation experiments to study the effect of language distances, language corpus size, and model size on calibration, and how multilingual models compare with their monolingual counterparts for diverse tasks and languages.
Using Semantic Information for Defining and Detecting OOD Inputs
This can render the current OOD detectors impermeable to inputs lying outside the training distribution but with the same semantic information (e. g. training class labels).
In and Out-of-Domain Text Adversarial Robustness via Label Smoothing
Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions).
Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
We propose a new method for classification which can improve robustness to distribution shifts, by combining expert knowledge about the ``high-level" structure of the data with standard classifiers.
Real-Time Detectors for Digital and Physical Adversarial Inputs to Perception Systems
To highlight this, we demonstrate the efficiency of the proposed detector on ImageNet, a task that is computationally challenging for the majority of relevant defenses, and on physically attacked traffic signs that may be encountered in real-time autonomy applications.
