Showing cs.HCShow all
2 papers · 1 filter
cs.HC2026
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…
cs.HC2025
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…