Large language models (LMs) offer unprecedented language generation capabilities and
exciting opportunities for interaction design. However, their highly context-dependent …

Robots that carry out tasks and interact in complex environments will inevitably commit
errors. Error detection is thus an important ability for robots to master, to work in an efficient …

Despite huge gains in performance in natural language understanding via large language
models in recent years, voice assistants still often fail to meet user expectations. In this study …

An overarching goal of Artificial Intelligence (AI) is creating autonomous, social agents that
help people. Two important challenges, though, are that different people prefer different …

For a robot to repair its own error, it must first know it has made a mistake. One way that
people detect errors is from the implicit reactions from bystanders-their confusion, smirks, or …

Despite the ubiquity of language models (LMs) in real-world applications (eg, web search,
text autocomplete, and content generation), most LMs are not optimized for, nor are they …

The computational systems we interact with are increasingly intelligent and dynamic, as they
learn from user interactions and are updated over time. Principles of good design highlight …

Robots that carry out tasks and interact in complex environments will inevitably commit
errors. Error detection is thus an essential ability for robots to master to work efficiently and …