Word co‐occurrence patterns in language corpora contain a surprising amount of
conceptual knowledge. Large language models (LLMs), trained to predict words in context …

Robust, faithful, and harm-free pronoun use for individuals is an important goal for language
model development as their use increases, but prior work tends to study only one or two of …

The Winograd Schema (WS) has been proposed as a test for measuring commonsense
capabilities of models. Recently, pre-trained language model-based approaches have …

The success of language models has inspired the NLP community to attend to tasks that
require implicit and complex reasoning, relying on human-like commonsense mechanisms …

Neural network language models appear to be increasingly aligned with how humans
process and generate language, but identifying their weaknesses through adversarial …

Recent literatures have shown that knowledge graph (KG) learning models are highly
vulnerable to adversarial attacks. However, there is still a paucity of vulnerability analyses of …

Recent studies show that many NLP systems are sensitive and vulnerable to a small
perturbation of inputs and do not generalize well across different datasets. This lack of …

Recent years have witnessed increasing interest in developing interpretable models in
Natural Language Processing (NLP). Most existing models aim at identifying input features …

Logical approaches to representing language have developed and evaluated computational
models of quantifier words since the 19th century, but today's NLU models still struggle to …

Unsupervised commonsense question answering is appealing since it does not rely on any
labeled task data. Among existing work, a popular solution is to use pre-trained language …