The field of natural language processing has seen impressive progress in recent years, with
neural network models replacing many of the traditional systems. A plethora of new models …

In the past few years, it has become increasingly evident that deep neural networks are not
resilient enough to withstand adversarial perturbations in input data, leaving them …

In reinforcement learning from human feedback, it is common to optimize against a reward
model trained to predict human preferences. Because the reward model is an imperfect …

We introduce Dynabench, an open-source platform for dynamic dataset creation and model
benchmarking. Dynabench runs in a web browser and supports human-and-model-in-the …

Adversarial examples highlight model vulnerabilities and are useful for evaluation and
interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens …

Recently, NLP has seen a surge in the usage of large pre-trained models. Users download
weights of models pre-trained on large datasets, then fine-tune the weights on a task of their …

With the development of high computational devices, deep neural networks (DNNs), in
recent years, have gained significant popularity in many Artificial Intelligence (AI) …

Pre-trained models of code have achieved success in many important software engineering
tasks. However, these powerful models are vulnerable to adversarial attacks that slightly …

In recent years, artificial intelligence technologies have been widely used in computer
vision, natural language processing, automatic driving, and other fields. However, artificial …

NLP has achieved great progress in the past decade through the use of neural models and
large labeled datasets. The dependence on abundant data prevents NLP models from being …