Self-correction is an approach to improving responses from large language models (LLMs)
by refining the responses using LLMs during inference. Prior work has proposed various self …

As large language models continue to develop in the field of AI, text generation systems are
susceptible to a worrisome phenomenon known as hallucination. In this study, we …

Spurred by advancements in scale, large language models (LLMs) have demonstrated the
ability to perform a variety of natural language processing (NLP) tasks zero-shot--ie, without …

While large language models (LLMs) have demonstrated remarkable capabilities across a
range of downstream tasks, a significant concern revolves around their propensity to exhibit …

The emergence of large language models (LLMs) has marked a significant breakthrough in
natural language processing (NLP), fueling a paradigm shift in information acquisition …

Generation of plausible yet incorrect factual information, termed hallucination, is an
unsolved issue in large language models. We study the ability of language models to …

Hallucination has been widely recognized to be a significant drawback for large language
models (LLMs). There have been many works that attempt to reduce the extent of …

Large Language Models (LLMs) have taken Knowledge Representation--and the world--by
storm. This inflection point marks a shift from explicit knowledge representation to a renewed …

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP).
Although convenient for research and practical applications, open-source LLMs with fewer …

Reasoning about time is of fundamental importance. Many facts are time-dependent. For
example, athletes change teams from time to time, and different government officials are …