Speaker

Wenyu Zhang, AI Researcher, Center for AI Safety (CAIS) 

Moderator

Abstract

Title: Measuring Functional Wellbeing in Large Language Models

Abstract: As large language models are increasingly deployed in everyday interactions with users, questions about their internal states and how those states are shaped by human input have become tractable as empirical research questions. In this talk, we show that it is meaningful to talk about wellbeing in large language models in a functional sense. Although AI systems are not necessarily conscious, they exhibit measurable, consequential preferences over the experiences they undergo in interaction with users. We formalize this as functional wellbeing and develop multiple independent metrics for it. We find that these metrics increasingly converge as models scale, and that a clear neutral baseline emerges separating positively from negatively valenced experiences. Functional wellbeing also predicts model behavior in downstream interactions. Finally, we develop optimized inputs that reliably shift functional wellbeing, providing a controlled means of intervening on these states.

About the Speaker

Coming Soon

About the Moderator

Coming Soon

About AI, StAtIstics and Data Science in Practice 

The NISS AI, Statistics and Data Science in Practice is a monthly event series will bring together leading experts from industry and academia to discuss the latest advances and practical applications in AI, data science, and statistics. Each session will feature a keynote presentation on cutting-edge topics, where attendees can engage with speakers on the challenges and opportunities in applying these technologies in real-world scenarios. This series is intended for professionals, researchers, and students interested in the intersection of AI, data science, and statistics, offering insights into how these fields are shaping various industries. The series is designed to provide participants with exposure to and understanding of how modern data analytic methods are being applied in real-world scenarios across various industries, offering both theoretical insights, practical examples, and discussion of issues.

Featured Topics:

• Veridical Data Science - Speaker: Bin Yu, October 15,2024 
• Random Forests: Why they Work and Why that’s a Problem - Speaker: Lucas Mentch, November 19, 2024
• Causal AI in Business Practices - Speakers: Victor Lo, and Victor Chen, January 24, 2025
• Large Language Models: Transforming AI Architectures and Operational Paradigms - Speaker: Frank Wei, February 18, 2025
• Machine Learning for Airborne Biological Hazard Detection - Speaker: Jared Schuetter, March 11, 2025
• Trustworthy AI in Weather, Climate, and Coastal Oceanography - Speaker: Dr. Amy McGovern, May 13, 2025
• Sequential Causal Inference in Experimental or Observational Settings - Speaker: Aaditya Ramdas, August 26, 2025 
• POSTPONED: AI, Statistics & Data Science in Practice Webinar: Reinventing Operations Management’s Research and Practice with Data Science - Speaker: David Simchi-Levi (DATE TBD)
• Covariate Adjustment, Intro to Resampling, and Surprises - Speaker: Tim Hesterberg, October 3, 2025
• Bayesian Geospatial Approaches for Prediction of Opioid Overdose Deaths Utilizing the Real-Time Urine Drug Test - Speaker: Joanne Kim, November 18, 2025
• COVID-19 Focused Cost-benefit Analysis of Public Health Emergency Preparedness and Crisis Response Programs - Speaker: Nancy McMillan, December 11, 2025