Related papers: The Keyhole Effect: Why Chat Interfaces Fail at Da…
Most task-oriented dialogue (TOD) benchmarks assume users that know exactly how to use the system by constraining the user behaviors within the system's capabilities via strict user goals, namely "user familiarity" bias. This data bias…
Conversational AI has a fundamental flaw as a knowledge interface: sycophantic chatbots induce epistemic entrenchment and delusional belief spirals even in rational agents. We propose the problem does not stem from the AI model, rooted…
The growing use of artificial intelligence (AI) in education, professional work, and everyday problem-solving has raised important questions about its effect on human reasoning. While AI can improve efficiency, save time, and support…
Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to…
People increasingly hold sustained, open-ended conversations with large language models (LLMs). Public reports and early studies suggest that, in such settings, models can reinforce delusional or conspiratorial ideation or even amplify…
Many different approaches for estimating the Interaction Quality (IQ) of Spoken Dialogue Systems have been investigated. While dialogues clearly have a sequential nature, statistical classification approaches designed for sequential…
The rise of Large Language Models (LLMs) like ChatGPT has advanced natural language processing, yet concerns about cognitive biases are growing. In this paper, we investigate the anchoring effect, a cognitive bias where the mind relies…
This paper introduces "Interaction as Intelligence" research series, presenting a reconceptualization of human-AI relationships in deep research tasks. Traditional approaches treat interaction merely as an interface for accessing AI…
The growing integration of artificial intelligence (AI) into human cognition raises a fundamental question: does AI merely improve efficiency, or does it alter how we think? This study experimentally tested whether short-term exposure to…
Large Language Models have become an integral part of new intelligent and interactive writing assistants. Many are offered commercially with a chatbot-like UI, such as ChatGPT, and provide little information about their inner workings. This…
The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks…
Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in…
Millions of users now design personalized LLM-based chatbots that shape their daily interactions, yet they can only roughly anticipate how their design choices will manifest as behaviors in deployment. This opacity is consequential:…
Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows…
The increasing progress in artificial intelligence and respective machine learning technology has fostered the proliferation of chatbots to the point where today they are being embedded into various human-technology interaction tasks. In…
Large language models improve with scale, yet feedback-based alignment still exhibits systematic deviations from intended behavior. Motivated by bounded rationality in economics and cognitive science, we view judgment as resource-limited…
With the emergence of conversational artificial intelligence (AI) agents, it is important to understand the mechanisms that influence users' experiences of these agents. We study a common tool in the designer's toolkit: conceptual…
Task interference, the performance degradation caused by task switches within a single conversation, has been studied exclusively in text-only settings despite the growing prevalence of multimodal dialogue systems. We introduce a benchmark…
The experience and adoption of conversational search is tied to the accuracy and completeness of users' mental models -- their internal frameworks for understanding and predicting system behaviour. Thus, understanding these models can…
It is popular lately to train large language models to be used as chat assistants, but in the conversation between the user and the chat assistant, there are prompts, require multi-turns between the chat assistant and the user. However,…