Skip to content
About
The CAISI Research Program at CIFAR
Our Community
Newsroom
Research
Contact
About
The CAISI Research Program at CIFAR
Our Community
Newsroom
Research
Contact
FR
|
EN
Research
Trustworthy & Interpretable AI
Catalyst Project
Democratic Alignment of LLMs Through Economic Theory: Relative Preferences and Strategic Coordination
Catalyst Project
Towards Socially Grounded AI Safety: Integrating Causal and Institutional Reasoning in Language Models
Catalyst Project
Performative Empathy and Deceptive Alignment
AI Alignment Project
Game-theoretic safety guarantees for advanced AI systems
AI Alignment Project
Sample-efficient online fine-tuning against resistant behaviors: statistical foundations for post-training alignment
AI Alignment Project
Scaling laws, data distributions, and learning dynamics: simulated high-energy physics data as a benchmark for data in the wild
AI Alignment Project
A unified statistical framework for quantifying rare event risks for language models
Catalyst Project
Advancing AI alignment through debate and shared normative reasoning
Catalyst Project
Adversarial robustness in knowledge graphs
Catalyst Project
Adversarial robustness of large language model (LLM) safety
Scroll To Top
