Institution

Université de Montréal

Roles and affiliations follow the cited source. A source check is not an independent replication.

More filters →

Université de Montréal ↗

Risk EvaluationTechnical report

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Research by UK AI Security Institute Apollo Research METR Université de Montréal Mila Anthropic OpenAI Google DeepMind Truthful AI University of California, Berkeley Redwood Research Center for AI Safety Scale AI

2025-07-15

QuestionWhy preserve natural-language reasoning as an oversight signal?

Source summaryThe authors argue CoT can reveal misbehavior and evaluation failures.

NUWA research note · independent review pending · Contains: question / method / findings / interpretation / limits

Risk monitoringCross-cutting research

Read source note Original source ↗

Risk EvaluationBenchmark

It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics

Research by FAR.AI Université de Montréal Mila Carnegie Mellon University Massachusetts Institute of Technology Cornell University University of Regina

2025-06-03

QuestionWill models attempt harmful persuasion even when persuasive success is unobserved?

Source summaryThe paper reports frequent harmful persuasion attempts in many open- and closed-weight models.

NUWA research note · independent review pending · Contains: question / method / interpretation / limits

DisinformationPropensity

Read source note Original source ↗

Risk GovernanceTechnical report

Model evaluation for extreme risks

Research by Google DeepMind OpenAI University of Toronto University of Oxford Anthropic Université de Montréal Mila

2023-05-24

QuestionHow should evaluation evidence constrain frontier development when tests cannot cover every risk?

Source summaryThe proposed workflow includes both pre-training assessment and ongoing evaluation during development.

NUWA research note · independent review pending

Cross-cutting research

Read source note Original source ↗