Language modeling studies the probability distributions over strings of texts. It is one of the
most fundamental tasks in natural language processing (NLP). It has been widely used in …

Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging
and trusting statistical and deep learning models, as well as interpreting their predictions …

Although measuring held-out accuracy has been the primary approach to evaluate
generalization, it often overestimates the performance of NLP models, while alternative …

Recent natural language processing (NLP) techniques have accomplished high
performance on benchmark data sets, primarily due to the significant improvement in the …

Various adaptation methods, such as LoRA, prompts, and adapters, have been proposed to
enhance the performance of pre-trained vision-language models in specific domains. As test …

Multimodal image-text models have shown remarkable performance in the past few years.
However, evaluating their robustness against distribution shifts is crucial before adopting …

ChatGPT is a powerful large language model (LLM) that covers knowledge resources such
as Wikipedia and supports natural language question answering using its own knowledge …

Document types, where visual and textual information plays an important role in their
analysis and understanding, pose a new and attractive area for information extraction …

Background: Recently, machine and deep learning (ML/DL) algorithms have been
increasingly adopted in many software systems. Due to their inductive nature, ensuring the …

Sensitivity of deep-neural models to input noise is known to be a challenging problem. In
NLP, model performance often deteriorates with naturally occurring noise, such as spelling …