8 papers
Dissociating the Internal Representations of Sycophancy in LLMs
Anthony Baez, Sheer Karny, Pat Pataranutaporn
Large Language Models (LLMs) frequently exhibit sycophancy, agreeing with a user's statement even when it is incorrect. While often studied as a single, uniform behavior, sycophanc…
Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift
Sheer Karny, Anthony Baez, Pat Pataranutaporn
Chatbot behavior is often opaque to users, as responses can shift unpredictably across a conversation, drifting toward sycophancy, toxicity, or other unsafe responses. This can lea…
AI-Wrapped: Participatory, Privacy-Preserving Measurement of Longitudinal LLM Use In-the-Wild
Cathy Mengying Fang, Sheer Karny, Chayapatr Archiwaranguprok +3
Alignment research on large language models (LLMs) increasingly depends on understanding how these systems are used in everyday contexts. Yet naturalistic interaction data is diffi…
Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI
Sheer Karny, Anthony Baez, Pat Pataranutaporn
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 beh…
Human-AI Collaboration: Trade-offs Between Performance and Preferences
Lukas William Mayer, Sheer Karny, Jackie Ayoub +4
Despite the growing interest in collaborative AI, designing systems that seamlessly integrate human input remains a major challenge. In this study, we developed a task to systemati…
Atlas of Human-AI Interaction (v1): An Interactive Meta-Science Platform for Large-Scale Research Literature Sensemaking
Chayapatr Archiwaranguprok, Awu Chen, Sheer Karny +3
Human-AI interaction researchers face an overwhelming challenge: synthesizing insights from thousands of empirical studies to understand how AI impacts people and inform effective…