相关论文: Exploring How Personality Models Information Visua…
Vision-language models are increasingly used to generate image captions in specific styles, such as humor or romantic. However, these transformer-based models often struggle with this subjective task in a zero-shot setting. While preference…
As large language models (LLMs) demonstrate increasingly advanced capabilities, aligning their behaviors with human values and preferences becomes crucial for their wide adoption. While previous research focuses on general alignment to…
User experience in data visualization is typically assessed through post-viewing self-reports, but these overlook the dynamic cognitive processes during interaction. This study explores the use of mind wandering -- a phenomenon where…
It is known that individual opinions on different policy issues often align to a dominant ideological dimension (e.g. "left" vs. "right") and become increasingly polarized. We provide an agent-based model that reproduces these two stylized…
Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance. We examine whether large language models (LLMs) exhibit…
Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their effectiveness, the effects of sampling and…
Voice User Interfaces (VUIs) increasingly leverage 'humanness' as a foundational design metaphor, adopting roles like 'assistants,' 'teachers,' and 'secretaries' to foster natural interactions. Yet, this approach can sometimes misalign user…
Large Language Models (LLMs) have demonstrated human-like capabilities in language comprehension and generation, becoming active participants in social and cognitive domains. This study investigates whether LLMs exhibit personality-like…
What can we learn about online users by comparing their profiles across different platforms? We use the term profile to represent displayed personality traits, interests, and behavioral patterns (e.g., offensiveness). We also use the term…
The current research used the contexts of U.S. presidential debates and negotiations to examine whether matching the linguistic style of an opponent in a two-party exchange affects the reactions of third-party observers. Building off…
Collaborative problem solving and learning are shaped by who or what is on the team. As large language models (LLMs) increasingly function as collaborators rather than tools, a key question is whether AI teammates can be aligned to express…
This paper examines the connection between the Five Factor Model personality traits and burnout in software developers. This study aims to validate generalizations of findings in other fields. An online survey consisting of a miniaturized…
Large language models (LLMs) are used to generate content for a wide range of tasks, and are set to reach a growing audience in coming years due to integration in product interfaces like ChatGPT or search engines like Bing. This intensifies…
Aligning large language models (LLMs) with human values and intents critically involves the use of human or AI feedback. While dense feedback annotations are expensive to acquire and integrate, sparse feedback presents a structural design…
Homophily -- our tendency to surround ourselves with others who share our perspectives and opinions about the world -- is both a part of human nature and an organizing principle underpinning many of our digital social networks. However,…
Natural language generation (NLG) models have emerged as a focal point of research within natural language processing (NLP), exhibiting remarkable performance in tasks such as text composition and dialogue generation. However, their…
Associative learning--forming links between co-occurring items--is fundamental to human cognition, reshaping internal representations in complex ways. Testing hypotheses on how representational changes occur in biological systems is…
Personalization despite being an effective solution to the problem information overload remains tricky on account of multiple dimensions to consider. Furthermore, the challenge of avoiding overdoing personalization involves estimation of a…
Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on…
Large language models exhibit sycophantic tendencies, but whether this behavior varies systematically with perceived user demographics is underexplored. Inspired by intersectionality (overlapping identities produce compounded effects), we…