User Base
Understanding user behavior and preferences is crucial for developing effective and ethical AI systems. Current research focuses on personalizing AI interactions, including adaptive summarization, recommendation systems (using techniques like graph neural networks and BERT), and assistive technologies, while also addressing challenges like user fatigue, privacy concerns (e.g., through differential privacy), and the potential for manipulation or deception by AI. This work is significant for improving the user experience across various applications and for mitigating potential harms associated with AI systems.
Papers
Rewarding Chatbots for Real-World Engagement with Millions of Users
Robert Irvine, Douglas Boubert, Vyas Raina, Adian Liusie, Ziyi Zhu, Vineet Mudupalli, Aliaksei Korshuk, Zongyi Liu, Fritz Cremer, Valentin Assassi, Christie-Carol Beauchamp, Xiaoding Lu, Thomas Rialan, William Beauchamp
Pacos: Modeling Users' Interpretable and Context-Dependent Choices in Preference Reversals
Qingming Li, H. Vicky Zhao
The AI Ghostwriter Effect: When Users Do Not Perceive Ownership of AI-Generated Text But Self-Declare as Authors
Fiona Draxler, Anna Werner, Florian Lehmann, Matthias Hoppe, Albrecht Schmidt, Daniel Buschek, Robin Welsch
Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting
Hai Dang, Sven Goller, Florian Lehmann, Daniel Buschek