5 papers
Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging
Tiancheng Hu, Benjamin Minixhofer, Nigel Collier
The "alignment tax" of post-training is typically framed as a drop in task accuracy. We show it also involves a severe loss of calibration, making models overconfident, less reliab…
SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
Tiancheng Hu, Joachim Baumann, Lorenzo Lupo +3
Large language model (LLM) simulations of human behavior have the potential to revolutionize the social and behavioral sciences, if and only if they faithfully reflect real human b…
When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning
Yijiang River Dong, Tiancheng Hu, Yinhong Liu +2
While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences ac…
International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications
Yoshua Bengio, Stephen Clare, Carina Prunkl +70
Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New training techniques that teach AI systems to re…
iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to News
Tiancheng Hu, Nigel Collier
Understanding how individuals perceive and react to information is fundamental for advancing social and behavioral sciences and developing human-centered AI systems. Current approa…