8 papers
Cultural Compass: A Framework for Organizing Societal Norms to Detect Violations in Human-AI Conversations
Myra Cheng, Vinodkumar Prabhakaran, Alice Oh +5
Generative AI models ought to be useful and safe across cross-cultural contexts. One critical step toward this goal is understanding how AI models adhere to sociocultural norms. Wh…
Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
Myra Cheng, Robert D. Hawkins, Dan Jurafsky
Large language models (LLMs) frequently fail to challenge users' harmful beliefs in domains ranging from medical advice to social reasoning. We argue that these failures can be und…
Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations
Sunny Yu, Ahmad Jabbar, Robert Hawkins +2
Different open-ended generation tasks require different degrees of output diversity. However, current LLMs are often miscalibrated. They collapse to overly homogeneous outputs for…
Attention to Non-Adopters
Kaitlyn Zhou, Kristina GligoriÄ, Myra Cheng +7
Although language model-based chat systems are increasingly used in daily life, most Americans remain non-adopters of chat-based LLMs -- as of June 2025, 66% had never used ChatGPT…
Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence
Myra Cheng, Cinoo Lee, Pranav Khadpe +3
Both the general public and academic communities have raised concerns about sycophancy, the phenomenon of artificial intelligence (AI) excessively agreeing with or flattering users…
ELEPHANT: Measuring and understanding social sycophancy in LLMs
Myra Cheng, Sunny Yu, Cinoo Lee +3
LLMs are known to exhibit sycophancy: agreeing with and flattering users, even at the cost of correctness. Prior work measures sycophancy only as direct agreement with users' expli…