Publications

2026

  1. Paper
    Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies
    Miles Brundage, Noemi Dreksler, Aidan Homewood, and 45 more authors
    2026

2025

  1. Paper
    Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse
    Steve Barrett, Malcolm Murray, Otter Quarks, and 17 more authors
    2025
  2. Paper
    A Methodology for Quantitative AI Risk Modeling
    Malcolm Murray, Steve Barrett, Henry Papadatos, and 5 more authors
    2025
  3. Paper
    The Role of Risk Modeling in Advanced AI Risk Management
    Chloé Touzet, Henry Papadatos, Malcolm Murray, and 6 more authors
    2025
  4. Paper
    Evaluating AI Companies’ Frontier Safety Frameworks: Methodology and Results
    Lily Stelling, Malcolm Murray, Simeon Campos, and 1 more author
    2025
  5. Research Memo
    Risk Tiers: Towards a Gold Standard for Advanced AI
    Nicholas A. Caputo, Siméon Campos, Stephen Casper, and 12 more authors
    2025
  6. Paper
    Evaluating the Goal-Directedness of Large Language Models
    Tom Everitt, Cristina Garbacea, Alexis Bellot, and 4 more authors
    2025
  7. Paper
    Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation
    Malcolm Murray*Henry Papadatos*, Otter Quarks, and 2 more authors
    2025
  8. Paper
    A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management
    Simeon Campos*Henry Papadatos*, Fabien Roger, and 3 more authors
    Conference on frontier AI safety frameworks (2024), 2025

2024

  1. Report
    Rating Frontier AI Developers’ Risk Management Maturity
    Henry Papadatos, Simeon Campos, and Malcolm Murray
    Conference on frontier AI safety frameworks, 2024
  2. Paper
    Linear Probe Penalties Reduce LLM Sycophancy
    Henry Papadatos, and Rachel Freedman
    SoLaR workshop, NeurIPS, 2024
  3. Blog post
    Your LLM Judge may be biased
    Henry Papadatos, and Rachel Freedman
    2024