Safety-Guaranteed LLMs

Share the event

As the landscape of artificial intelligence evolves, ensuring the safety and alignment of superintelligent language models (LLMs) is paramount. This workshop will delve into the theoretical foundations of LLM safety. This could include topics like the Bayesian view of LLM safety versus the RL view of safety and other theories.

The flavor of this workshop is futuristic, focusing on how to ensure a superintelligent LLM/AI remains safe and aligned with humans.  This workshop is a joint effort of the Simons Institute and IVADO.

Key Topics:

  • Bayesian Approaches to LLM Safety
  • Reinforcement Learning Perspectives on Safety
  • Theoretical Frameworks for Ensuring AI Alignment
  • Case Studies and Practical Implications
  • Future Directions in LLM Safety Research

This workshop is part of the programming for the thematic semester on Large Language Models and Transformers, organized in collaboration with the Simons Institute for the Theory of Computing.

Travel grants are available to attend the event in California.

Workshops will also be available online and live (registration required).

Organizers

Yoshua Bengio (IVADO - Mila - Université de Montréal)
Siva Reddy (IVADO - Mila - McGill University)
Sasha Rush (Cornell University)
Umesh Vazirani (Simons Institute, UC Berkeley)

AGENDA

Monday, Apr. 14th, 2025

9 – 9:15 a.m.: Coffee and Check-In
9:15 – 9:30 a.m.: Welcome Address
9:30 – 10:30 a.m.: Simulating Counterfactual Training
    Roger Grosse (University of Toronto)
10:30 – 11 a.m.: Break
11 a.m. – 12 p.m.: AI Safety via Inference-Time Compute
    Boaz Barak (Harvard University and OpenAI)
12 – 2 p.m.: Lunch (on your own)
2 – 3 p.m.: Future Directions in AI Safety Research
    Dawn Song (UC Berkeley)
3 – 3:30 p.m.: Break
3:30 – 4:30 p.m.: Scalable AI Safety via Efficient Debate Games
    Georgios Piliouras (Singapore University of Technology and Design)
4:30 – 6 p.m.: Reception

Tuesday, Apr. 15th, 2025

9:30 – 10 a.m.: Coffee and Check-In
10 – 11 a.m: Full-Stack Alignment
    Ryan Lowe (Meaning Alignment Institute)
11 – 11:30 a.m.: Break
11:30 a.m. – 12:30 p.m.: Can We Get Asymptotic Safety Guarantees Based On Scalable Oversight?
    Geoffrey Irving (UK AI Security Institute)
12:30 – 2:30 p.m.: Lunch (on your own)
2:30 – 3:30 p.m.: Amortised Inference Meets LLMs: Algorithms and Implications for Faithful Knowledge Extraction
    Nikolay Malkin (University of Edinburgh)
3:30 – 4 p.m.: Break
4 – 5 p.m.: Special Lecture – Richard M. Karp Distinguished Lecture
    Yoshua Bengio (IVADO – Université de Montréal – Mila)
5 – 6 p.m.: Panel Discussion
    
Yoshua Bengio (IVADO – Mila – Université de Montréal), Dawn Song (UC Berkeley), Roger Grosse, Geoffrey Irving, Siva Reddy (IVADO – Mila – McGill University)

Wednesday, Apr. 16th, 2025

8:30 – 9 a.m.: Coffee and Check-In
9 – 10 a.m.: Talk By
    Siva Reddy (IVADO – McGill University – Mila)
10 – 10:15 a.m.: Break
10:15 – 11:15 a.m.: Adversarial Training for LLMs’ Safety Robustness
    Gauthier Gidel (IVADO – Université de Montréal – Mila)
11:15 – 11:30 a.m.: Break
11:30am – 12:30 p.m.: Talk By
    Zico Kolter (Carnegie Mellon University)
12:30 – 2 p.m.: Lunch (on your own)
2 – 3 p.m.: Causal Representation Learning: A Natural Fit for Mechanistic Interpretability
    Dhanya Sridhar (IVADO – Université de Montréal – Mila)
3 – 3:15 p.m.: Break
3:15 – 4:15 p.m.: Out of Distribution, Out of Control? Understanding Safety Challenges in AI
    Aditi Raghunathan (Carnegie Mellon University)

Thursday, Apr. 17th, 2025

9 – 9:30 a.m.: Coffee and Check-In
9:30 – 10:30 a.m.: LLM Negotiations and Social Dilemmas
    Aaron Courville (IVADO – Université de Montréal – Mila)
10:30 – 11 a.m.: Break
11 a.m. – 12 p.m: Scalably Understanding AI With AI
    Jacob Steinhardt (UC Berkeley)
12 – 1:45 p.m.: Lunch (on your own)
1:45 – 2:45 p.m.: Controlling Untrusted AIs with Monitors
    Ethan Perez (Anthropic)
2:45 – 3 p.m.: Break
3 – 4 p.m.: What Can Theory of Cryptography Tell us About AI Safety
    Shafi Goldwasser (UC Berkeley)
4 – 5 p.m.: Assessing the Risk of Advanced Reinforcement Learning Agents Causing Human Extinction
    Michael Cohen (UC Berkeley)

Friday, Apr. 18th, 2025

8:30 – 9 a.m.: Coffee and Check-In
9 – 10 a.m.: Safeguarded AI Workflows
    David Dalrymple (Advanced Research + Invention Agency)
10 – 10:15 a.m.: Break
10:15 – 11:15 a.m.: AI Safety: LLMs, Facts, Lies, and Agents in the Real World
    Chris Pal (IVADO + Polytechnique + Mila + UdeM DIRO + CIFAR + ServiceNow)
11:15 – 11:30 a.m.: Break
11:30 a.m. – 12:30 p.m.: Measurements for Capabilities and Hazards
    Dan Hendrycks (Center for AI Safety)
12:30 – 2 p.m.: Lunch (on your own)
2 – 3 p.m.: Theoretical and Empirical aspects of Singular Learning Theory for AI Alignment
    Daniel Murfet (Timaeus)
3 – 3:30 p.m.: Break
3:30 – 4:30 p.m.: Probabilistic Safety Guarantees Using Model Internals
    Jacob Hilton (Alignment Research Center)
4:30 – 4:45 p.m: Closing Remarks