182 citations · 190 across the 8 of their papers we have counts for
4 papers · 1 filter
Open Benchmark of AI Impact on Humans (ImpactBench): an expert-guided, open platform for the holistic evaluation of AI impact on humans
Chayapatr Archiwaranguprok, Krystal Kirkland, Rachel Poonsiriwong +17
The present work is concerned with how to measure, at scale, the multi-dimensional impact of generative AI models on the individuals who use them. In service of this goal, we intro…
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…
Surfacing Neural Activations Over Multi-Turn Conversation Improves User Calibration to LLM Behavioral Drift
Sheer Karny, Anthony Baez, Pat Pataranutaporn
Current human-AI interaction (HAI) only surfaces model outputs, hiding how LLM behavior can shift unpredictably toward unsafe behaviors in multi-turn conversations, potentially und…
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…