Language models (LMs) have demonstrated remarkable capabilities across a wide range of
tasks in various domains. Despite their impressive performance, the reliability of their output …

The task of empowering large language models (LLMs) to accurately express their
confidence, referred to as confidence elicitation, is essential in ensuring reliable and …

Large language models (LLMs) have demonstrated remarkable capabilities across a wide
range of tasks in various domains. Despite their impressive performance, they can be …

As large language models continue to be widely developed, robust uncertainty
quantification techniques will become crucial for their safe deployment in high-stakes …

Large Language Models (LLMs) are increasingly used for accessing information on the web.
Their truthfulness and factuality are thus of great interest. To help users make the right …

Sequence generation models are increasingly being used to translate natural language into
programs, ie, to perform executable semantic parsing. The fact that semantic parsing aims to …

Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning.
Recent multi-modal OOD detection leverages textual information from in-distribution (ID) …

_Uncertainty expressions_ such as" probably" or" highly unlikely" are pervasive in human
language. While prior work has established that there is population-level agreement in terms …

Abstract Language models (LMs) are statistical models trained to assign probability to
humangenerated text. As such, it is reasonable to question whether they approximate …

A wide body of evidence shows that human language processing difficulty is predicted by
the information-theoretic measure surprisal, a word's negative log probability in context …