Henry Papadatos

According to our database, Henry Papadatos authored at least 4 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Evaluating the Goal-Directedness of Large Language Models.

Tom Everitt, Cristina Garbacea, Alexis Bellot, Jonathan Richens, Henry Papadatos, Siméon Campos, Rohin Shah

CoRR, April, 2025

Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation.

Malcolm Murray, Henry Papadatos, Otter Quarks, Pierre-François Gimenez, Siméon Campos

CoRR, March, 2025

A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management.

Siméon Campos, Henry Papadatos, Fabien Roger, Chloé Touzet, Otter Quarks, Malcolm Murray

CoRR, February, 2025

2024

Linear Probe Penalties Reduce LLM Sycophancy.

Henry Papadatos, Rachel Freedman

CoRR, 2024