Publications

2026

1. Report

   GLM-5.2 Risk Evaluation Report

   Chinmayi Dixit^*, Jacob Davies^*, Jasmine Li, Ben Snodin, Jack Kengott, and 1 more author

   2026

   PDF
2. Report

   Draft Articles on the Safe Development and Diffusion of Artificial Intelligence

   José Jaime Villalobos, Duncan Cass-Beggs, Guillem Bas, Mark Brakel, Siméon Campos, and 21 more authors

   Future of Life Institute and Centre for International Governance Innovation, 2026

   PDF Website
3. Paper

   Lessons from External Review of DeepMind’s Scheming Inability Safety Case

   Stephen Barrett, Francisco Javier Campos Zabala, Sean P. Fillingham, Umair Siddique, James Walpole, and 2 more authors

   TAIGR Workshop, ICML, 2026

   Best Paper arXiv Bib

   Best Paper Award and selected for an oral presentation at the TAIGR Workshop, ICML 2026.

   @article{barrett2026lessonsexternalreviewdeepminds,
     title = {Lessons from External Review of DeepMind's Scheming Inability Safety Case},
     author = {Barrett, Stephen and Zabala, Francisco Javier Campos and Fillingham, Sean P. and Siddique, Umair and Walpole, James and Bloomfield, Robin and Papadatos, Henry},
     year = {2026},
     journal = {TAIGR Workshop, ICML},
     eprint = {2604.21964},
     archiveprefix = {arXiv},
     primaryclass = {cs.CY},
     url = {https://arxiv.org/abs/2604.21964},
   }

4. Paper

   Open Problems in Frontier AI Risk Management

   Marta Ziosi, Miro Plueckebaum, Stephen Casper, Henry Papadatos, Ze Shen Chin, and 24 more authors

   2026

   Bib PDF

   @article{ziosi2026openproblemsfrontier,
     title = {Open Problems in Frontier AI Risk Management},
     author = {Ziosi, Marta and Plueckebaum, Miro and Casper, Stephen and Papadatos, Henry and Chin, Ze Shen and Slattery, Peter and Gealy, James and Rudner, Tim G. J. and Tse, Brian and Gil, Ariel and Paskov, Patricia and Negele, Maximilian and Gipiškis, Rokas and Madkour, Nada and Lummis, Vera and Jain, Rupal and Eder, Luise and Fort, Kristina and van Draanen Glismann, Malou C. and Belhadj, Inès and Oueslati, Amin and Wisakanto, Anna K. and Mallah, Richard and Holtman, Koen and Zuhdi, Ranj and Schiff, Daniel S. and Newman, Jessica and Murray, Malcolm and Trager, Robert},
     year = {2026},
   }

5. Paper

   Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies

   Miles Brundage, Noemi Dreksler, Aidan Homewood, Sean McGregor, Patricia Paskov, and 43 more authors

   2026

   arXiv Bib

   @article{brundage2026frontieraiauditingrigorous,
     title = {Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies},
     author = {Brundage, Miles and Dreksler, Noemi and Homewood, Aidan and McGregor, Sean and Paskov, Patricia and Stosz, Conrad and Sastry, Girish and Cooper, A. Feder and Balston, George and Adler, Steven and Casper, Stephen and Anderljung, Markus and Werner, Grace and Mindermann, Soren and Mavroudis, Vasilios and Bucknall, Ben and Stix, Charlotte and Freund, Jonas and Pacchiardi, Lorenzo and Hernandez-Orallo, Jose and Pistillo, Matteo and Chen, Michael and Painter, Chris and Ball, Dean W. and O'Keefe, Cullen and Weil, Gabriel and Harack, Ben and Finley, Graeme and Hassan, Ryan and Emmons, Scott and Foster, Charles and Reuel, Anka and Treece, Bri and Bengio, Yoshua and Reti, Daniel and Bommasani, Rishi and Trout, Cristian and Shamsabadi, Ali Shahin and Dattani, Rajiv and Weller, Adrian and Trager, Robert and Sevilla, Jaime and Wagner, Lauren and Soder, Lisa and Ramakrishnan, Ketan and Papadatos, Henry and Murray, Malcolm and Tovcimak, Ryan},
     year = {2026},
     eprint = {2601.11699},
     archiveprefix = {arXiv},
     primaryclass = {cs.CY},
     url = {https://arxiv.org/abs/2601.11699},
   }

2025

1. Paper

   Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse

   Steve Barrett, Malcolm Murray, Otter Quarks, Matthew Smith, Jakub Kryś, and 15 more authors

   2025

   arXiv Bib

   @article{barrett2025quantitativemodelingcybersecurityrisks,
     title = {Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse},
     author = {Barrett, Steve and Murray, Malcolm and Quarks, Otter and Smith, Matthew and Kryś, Jakub and Campos, Siméon and Boria, Alejandro Tlaie and Touzet, Chloé and Hayrapet, Sevan and Heiding, Fred and Nevo, Omer and Swanda, Adam and Aguirre, Jair and Gershovich, Asher Brass and Clay, Eric and Fetterman, Ryan and Fritz, Mario and Juarez, Marc and Mavroudis, Vasilios and Papadatos, Henry},
     year = {2025},
     eprint = {2512.08864},
     archiveprefix = {arXiv},
     primaryclass = {cs.CY},
     url = {https://arxiv.org/abs/2512.08864},
   }

2. Paper

   A Methodology for Quantitative AI Risk Modeling

   Malcolm Murray, Steve Barrett, Henry Papadatos, Otter Quarks, Matt Smith, and 3 more authors

   2025

   arXiv Bib

   @article{murray2025methodologyquantitativeairisk,
     title = {A Methodology for Quantitative AI Risk Modeling},
     author = {Murray, Malcolm and Barrett, Steve and Papadatos, Henry and Quarks, Otter and Smith, Matt and Boria, Alejandro Tlaie and Touzet, Chloé and Campos, Siméon},
     year = {2025},
     eprint = {2512.08844},
     archiveprefix = {arXiv},
     primaryclass = {cs.CY},
     url = {https://arxiv.org/abs/2512.08844},
   }

3. Paper

   The Role of Risk Modeling in Advanced AI Risk Management

   Chloé Touzet, Henry Papadatos, Malcolm Murray, Otter Quarks, Steve Barrett, and 4 more authors

   2025

   arXiv Bib

   @article{touzet2025roleriskmodelingadvanced,
     title = {The Role of Risk Modeling in Advanced AI Risk Management},
     author = {Touzet, Chloé and Papadatos, Henry and Murray, Malcolm and Quarks, Otter and Barrett, Steve and Boria, Alejandro Tlaie and Perrier, Elija and Smith, Matthew and Campos, Siméon},
     year = {2025},
     eprint = {2512.08723},
     archiveprefix = {arXiv},
     primaryclass = {cs.CY},
     url = {https://arxiv.org/abs/2512.08723},
   }

4. Paper

   Evaluating AI Companies’ Frontier Safety Frameworks: Methodology and Results

   Lily Stelling, Malcolm Murray, Simeon Campos, and Henry Papadatos

   2025

   arXiv Bib

   @article{stelling2025evaluatingaicompaniesfrontier,
     title = {Evaluating AI Companies' Frontier Safety Frameworks: Methodology and Results},
     author = {Stelling, Lily and Murray, Malcolm and Campos, Simeon and Papadatos, Henry},
     year = {2025},
     eprint = {2512.01166},
     archiveprefix = {arXiv},
     primaryclass = {cs.CY},
     url = {https://arxiv.org/abs/2512.01166},
   }

5. Book

   France 2040, fragments d’avenir

   Jacques Attali, Edgar Morin, François Hollande, Enrico Letta, Stéphane Bancel, and 43 more authors

   Flammarion. Contribution: “2040: tirer le meilleur parti de l’IA ou la subir?” co-written with Chloé Touzet and Siméon Campos (pp. 357–374) , 2025

   Bib

   @book{attali2025france2040,
     title = {France 2040, fragments d'avenir},
     author = {Attali, Jacques and Morin, Edgar and Hollande, François and Letta, Enrico and Bancel, Stéphane and Basch, Lucie and Béllot, Cécile and Bronner, Gérald and Cagé, Agathe and Campos, Siméon and Castets, Lucie and Delaporte, Arthur and Delfraissy, Jean-François and Delorme, Angélique and Devillers, Laurence and Ecalle, François and Filippova, Diana and Flahault, Antoine and Fouks, Stéphane and Gallois, Louis and Guimier, Lucie and Hainaut, Béatrice and Haziza, Emma and Jouvet, Pierre and Kerivel, Aude and Kermarrec, Anne-Marie and Koenig, Gaspard and Lokiec, Pascal and Luksha, Pavel and {Levy Provençal}, Michel and {Le Bras}, Hervé and Martinez, Julie and Méda, Dominique and Morel, Benjamin and Morin, Chloé and Naves, Marie-Cécile and Orsenna, Erik and Oudéa-Castéra, Amélie and Papadatos, Henry and Policar, Alain and Sénéclauze, Caroline and Senik, Claudia and Sonnac, Nathalie and Taddei, François and Tir, Sonia and Touzet, Chloé and Tubiana, Laurence and Viard, Jean},
     editor = {Attali, Jacques},
     year = {2025},
     publisher = {Flammarion},
     address = {Paris},
     isbn = {9782080491268},
   }

6. Research Memo

   Risk Tiers: Towards a Gold Standard for Advanced AI

   Nicholas A. Caputo, Siméon Campos, Stephen Casper, James Gealy, Bosco Hung, and 10 more authors

   2025

   PDF
7. Paper

   Evaluating the Goal-Directedness of Large Language Models

   Tom Everitt, Cristina Garbacea, Alexis Bellot, Jonathan Richens, Henry Papadatos, and 2 more authors

   2025

   arXiv Bib

   @article{everitt2025evaluatinggoaldirectednesslargelanguage,
     title = {Evaluating the Goal-Directedness of Large Language Models},
     author = {Everitt, Tom and Garbacea, Cristina and Bellot, Alexis and Richens, Jonathan and Papadatos, Henry and Campos, Siméon and Shah, Rohin},
     year = {2025},
     eprint = {2504.11844},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
     url = {https://arxiv.org/abs/2504.11844},
   }

8. Paper

   Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation

   Malcolm Murray^*, Henry Papadatos^*, Otter Quarks, Pierre-François Gimenez, and Simeon Campos

   2025

   arXiv Bib

   @article{murray2025mappingaibenchmark,
     title = {Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation},
     author = {Murray, Malcolm and Papadatos, Henry and Quarks, Otter and Gimenez, Pierre-François and Campos, Simeon},
     year = {2025},
     eprint = {2503.04299},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
     url = {https://arxiv.org/abs/2503.04299},
   }

9. Paper

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

   Simeon Campos^*, Henry Papadatos^*, Fabien Roger, Chloé Touzet, Otter Quarks, and 1 more author

   Conference on frontier AI safety frameworks (2024), 2025

   arXiv Bib

   @article{campos2025afrontierairisk,
     title = {A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management},
     author = {Campos, Simeon and Papadatos, Henry and Roger, Fabien and Touzet, Chloé and Quarks, Otter and Murray, Malcolm},
     year = {2025},
     eprint = {2502.06656},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
     url = {https://arxiv.org/abs/2502.06656},
     journal = {Conference on frontier AI safety frameworks (2024)},
   }

2024

1. Report

   Rating Frontier AI Developers’ Risk Management Maturity

   Henry Papadatos, Simeon Campos, and Malcolm Murray

   Conference on frontier AI safety frameworks, 2024

   PDF Website
2. Paper

   Linear Probe Penalties Reduce LLM Sycophancy

   Henry Papadatos, and Rachel Freedman

   SoLaR workshop, NeurIPS, 2024

   arXiv Bib

   @article{papadatos2024linearprobepenaltiesreduce,
     title = {Linear Probe Penalties Reduce LLM Sycophancy},
     author = {Papadatos, Henry and Freedman, Rachel},
     year = {2024},
     eprint = {2412.00967},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
     journal = {SoLaR workshop, NeurIPS},
   }

3. Blog post

   Your LLM Judge may be biased

   Henry Papadatos, and Rachel Freedman

   2024

   Blog