Fabien Roger

Identifiers

• name variant Fabien Roger 0.60 · backfill

Papers (7)

1. SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors cs.CR · 2026 · author #4
2. Classifier Context Rot: Monitor Performance Degrades with Context Length cs.AI · 2026 · author #2
3. How Useful Is Cross-Domain Generalization for Training LLM Monitors? cs.AI · 2026 · author #2
4. Narrow Secret Loyalty Dodges Black-Box Audits cs.CR · 2026 · author #2
5. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety cs.AI · 2025 · author #32
6. Reasoning Models Don't Always Say What They Think cs.CL · 2025 · author #10
7. Alignment faking in large language models cs.AI · 2024 · author #4

Mentions

• 2507.11473 #32 · arxiv_oai · confidence 0.70 Fabien Roger
• 2605.16626 #4 · arxiv_oai · confidence 0.70 Fabien Roger

Frequent Coauthors

• Ethan Perez 3 shared papers
• Joe Benton 3 shared papers
• Buck Shlegeris 2 shared papers
• Carson Denison 2 shared papers
• Evan Hubinger 2 shared papers
• Jared Kaplan 2 shared papers
• Jonathan Uesato 2 shared papers
• Julian Michael 2 shared papers
• Ryan Greenblatt 2 shared papers
• Sam Martin 2 shared papers
• Samuel R. Bowman 2 shared papers
• Vlad Mikulik 2 shared papers
• Akbir Khan 1 shared papers
• Alan Cooney 1 shared papers
• Aleksander M\k{a}dry 1 shared papers
• Alfie Lamerton 1 shared papers
• Allan Dafoe 1 shared papers
• Anca Dragan 1 shared papers
• Ansh Radhakrishnan 1 shared papers
• Arushi Somani 1 shared papers