10 papers
Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethics
Jessica Y. Bo, Paula Akemi Aoyagui, Shalaleh Rismani +3
Safety risks of AI are becoming increasingly evident in human interactions with AI technologies. The prominent approaches to evaluating these risks favor technical methods, such as…
Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulation
Seth Grief-Albert, Jessica Bo, Difan Jiao +1
Large language models are increasingly used to simulate human opinions, but prior work reports conflicting results: some studies find promising alignment with human survey data, wh…
Large Language Lovers: Lived Experiences of Negotiating Agency and Platform Control in AI Companionship
Patrick Yung Kang Lee, Jessica Y. Bo, Zixin Zhao +6
Individuals are turning to increasingly anthropomorphic, general-purpose chatbots for AI companionship, rather than roleplay-specific platforms. However, not much is known about ho…
What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct
Meryl Ye, Lujain Ibrahim, Jessica Y. Bo +5
AI sycophancy has become a prominent concern in large language model (LLM) research. Yet the term lacks a consistent definition and has been applied to behaviors ranging from agree…
Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts
Jessica Y. Bo, Lillio Mok, Ashton Anderson
Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algo…
Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks
Jessica Y. Bo, Majeed Kazemitabaar, Mengqing Deng +2
Sycophancy, the tendency of LLM-based chatbots to express excessive agreement with their users, even when inappropriate, is emerging as a significant risk in human-AI interactions.…