Related papers: Vulnerability-Amplifying Interaction Loops: a syst…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Multi-modal Large Language Models (MLLMs) are increasingly deployed in interactive applications. However, their safety vulnerabilities become pronounced in multi-turn multi-modal scenarios, where harmful intent can be gradually…
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:…
Our work addresses the challenges older adults face with commercial Voice Assistants (VAs), notably in conversation breakdowns and error handling. Traditional methods of collecting user experiences-usage logs and post-hoc interviews-do not…
Amidst the growing interest in developing task-autonomous AI for automated mental health care, this paper addresses the ethical and practical challenges associated with the issue and proposes a structured framework that delineates levels of…
As a general purpose technology without a concrete pre-defined purpose, personal chatbots can be used for a whole range of objectives, depending on the personal needs, contexts, and tasks of an individual, and so potentially impact a…
AI systems fail silently far more often than they fail visibly. In an analysis of 100K human-AI interactions from the WildChat dataset, we find that 79% of AI failures are invisible: something went wrong but the user gave no overt…
This article explores the phenomenon of confirmation bias in generative AI chatbots, a relatively underexamined aspect of AI-human interaction. Drawing on cognitive psychology and computational linguistics, it examines how confirmation…
The conversational nature of chatbots poses challenges to designers since their development is different from other software and requires investigating new practices in the context of human-AI interaction and their impact on user…
Millions of patients are already using large language model (LLM) chatbots for medical advice on a regular basis, raising patient safety concerns. This physician-led red-teaming study compares the safety of four publicly available…
We introduce Vibe-Eval: a new open benchmark and framework for evaluating multimodal chat models. Vibe-Eval consists of 269 visual understanding prompts, including 100 of hard difficulty, complete with gold-standard responses authored by…
As large language models (LLMs) increasingly mediate emotionally sensitive conversations, especially in mental health contexts, their ability to recognize and respond to high-risk situations becomes a matter of public safety. This study…
Chat has become the default interface for AI-assisted data analysis. For multi-step, state-dependent analytical tasks, this is a mistake. Building on Woods (1984) Keyhole Effect, the cognitive cost of viewing large information spaces…
Large Language Model (LLMs) such as ChatGPT that exhibit generative AI capabilities are facing accelerated adoption and innovation. The increased presence of Generative AI (GAI) inevitably raises concerns about the risks and safety…
The use of large language model (LLM)-based AI chatbots among college students has increased rapidly, yet little is known about how individual psychological attributes shape students' interaction patterns with these technologies. This…
Conventional Voice Assistants (VAs) rely on traditional language models to discern user intent and respond to their queries, leading to interactions that often lack a broader contextual understanding, an area in which Large Language Models…
Large Language Models (LLMs) have significantly advanced user-bot interactions, enabling more complex and coherent dialogues. However, the prevalent text-only modality might not fully exploit the potential for effective user engagement.…
The rise of LLMs has deflected a growing portion of human-computer interactions towards LLM-based chatbots. The remarkable abilities of these models allow users to interact using long, diverse natural language text covering a wide range of…
As AI chatbots become ubiquitous, voice interaction presents a compelling way to enable rapid, high-bandwidth communication for both semantic and social signals. This has driven research into Large Audio Models (LAMs) to power voice-native…
With the rapid adoption of LLM-based chatbots, there is a pressing need to evaluate what humans and LLMs can achieve together. However, standard benchmarks, such as MMLU, measure LLM capabilities in isolation (i.e., "AI-alone"). Here, we…