We survey applications of pretrained foundation models in robotics. Traditional deep
learning models in robotics are trained on small datasets tailored for specific tasks, which …

A prominent weakness of modern language models (LMs) is their tendency to generate
factually incorrect text, which hinders their usability. A natural question is whether such …

The increased deployment of LMs for real-world tasks involving knowledge and facts makes
it important to understand model epistemology: what LMs think they know, and how their …

Despite efforts to expand the knowledge of large language models (LLMs), knowledge gaps-
-missing or outdated information in LLMs--might always persist given the evolving nature of …

Artificial Intelligence (AI) use in automated Electrocardiogram (ECG) classification has
continuously attracted the research community's interest, motivated by their promising …

As Large Language Models (LLMs) are nondeterministic, the same input can generate
different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may …

Large Language Models (LLMs) have shown great potential in Natural Language
Processing (NLP) tasks. However, recent literature reveals that LLMs generate nonfactual …

Fine-tuned Large Language Models (LLMs) often suffer from overconfidence and poor
calibration, particularly when fine-tuned on small datasets. To address these challenges, we …

Uncertainty estimation is a necessary component when implementing AI in high-risk
settings, such as autonomous cars, medicine, or insurances. Large Language Models …

From common-sense reasoning to domain-specific tasks, parameter-efficient fine tuning
(PEFT) methods for large language models (LLMs) have showcased significant performance …