Search for: All records

It was submitted and is under review. 

Dialog systems (e.g., chatbots) have been widely studied, yet related research that leverages artificial intelligence (AI) and natural language processing (NLP) is constantly evolving. These systems have typically been developed to interact with humans in the form of speech, visual, or text conversation. As humans continue to adopt dialog systems for various objectives, there is a need to involve humans in every facet of the dialog development life cycle for synergistic augmentation of both the humans and the dialog system actors in real-world settings. We provide a holistic literature survey on the recent advancements inhuman-centered dialog systems(HCDS). Specifically, we provide background context surrounding the recent advancements in machine learning-based dialog systems and human-centered AI. We then bridge the gap between the two AI sub-fields and organize the research works on HCDS under three major categories (i.e., Human-Chatbot Collaboration, Human-Chatbot Alignment, Human-Centered Chatbot Design & Governance). In addition, we discuss the applicability and accessibility of the HCDS implementations through benchmark datasets, application scenarios, and downstream NLP tasks. 

Geospatial data visualization on a map is an essential tool for modern data exploration tools. However, these tools require users to manually configure the visualization style including color scheme and attribute selection, a process that is both complex and domain-specific. Large Language Models (LLMs) provide an opportunity to intelligently assist in styling based on the underlying data distribution and characteristics. This paper demonstrates LASEK, an LLM-assisted visualization framework that automates attribute selection and styling in large-scale spatio-temporal datasets. The system leverages LLMs to determine which attributes should be highlighted for visual distinction and even suggests how to integrate them in styling options improving interpretability and efficiency. We demonstrate our approach through interactive visualization scenarios, showing how LLM-driven attribute selection enhances clarity, reduces manual effort, and provides data-driven justifications for styling decisions. 

A significant body of research is dedicated to developing language models that can detect various types of online abuse, for example, hate speech, cyberbullying. However, there is a disconnect between platform policies, which often consider the author's intention as a criterion for content moderation, and the current capabilities of detection models, which typically lack efforts to capture intent. This paper examines the role of intent in the moderation of abusive content. Specifically, we review state-of-the-art detection models and benchmark training datasets to assess their ability to capture intent. We propose changes to the design and development of automated detection and moderation systems to improve alignment with ethical and policy conceptualizations of these abuses.