Assessment and evaluation have long been critical challenges in artificial intelligence (AI)
and natural language processing (NLP). However, traditional methods, whether matching …

Abstract Concept Bottleneck Models (CBMs) map the black-box visual representations
extracted by deep neural networks onto a set of interpretable concepts and use the concepts …

Aligned Large Language Models (LLMs) showcase remarkable versatility, capable of
handling diverse real-world tasks. Meanwhile, aligned LLMs are also expected to exhibit …

In this work, we tackle the scenario of understanding characters in scripts, which aims to
learn the characters' personalities and identities from their utterances. We begin by …

Knowledge tracing (KT) plays a crucial role in predicting students' future performance by
analyzing their historical learning processes. Deep neural networks (DNNs) have shown …

Knowledge tracing (KT) aims to estimate student's knowledge mastery based on their
historical interactions. Recently, the deep learning based KT (DLKT) approaches have …

Modeling lexical semantics is a challenging task, often suffering from interpretability pitfalls.
In this paper, we delve into the generation of dictionary-like sense definitions and explore …

Due to the ever-increasing complexity of income tax laws in the United States, the number of
US taxpayers filing their taxes using tax preparation software (henceforth, tax software) …

Providing example sentences that are diverse and aligned with learners {'} proficiency levels
is essential for fostering effective language acquisition. This study examines the use of Pre …

This PhD thesis focuses on computational modeling of semantic change through large
language models. It investigates the modeling of lexical semantic change, where words …