@article{barez2025cotnotexplainability,
  category = {Interpretability},
  title = {Chain-of-Thought Is Not Explainability},
  author = {Barez, Fazl and Wu, Tung-Yu and Arcuschin, Iv{\'a}n and Lan, Michael and Wang, Vincent and Siegel, Noah and Collignon, Nicolas and Neo, Clement and Lee, Isabelle and Paren, Alasdair and Bibi, Adel and Trager, Robert and Fornasiere, Damiano and Yan, John and Elazar, Yanai and Bengio, Yoshua},
  journal = {Under review},
  year = {2025},
}

@inproceedings{neo2025vlm,
  category = {Interpretability},
  title = {Towards Interpreting Visual Information Processing in Vision-Language Models},
  author = {Neo, Clement and Ong, Luke and Torr, Philip and Geva, Mor and Krueger, David and Barez, Fazl},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
}

@inproceedings{marks2024ilfp,
  category = {Interpretability},
  title = {Interpreting Learned Feedback Patterns in Large Language Models},
  author = {Marks, Luke and Abdullah, Amir and Neo, Clement and Arike, Rauno and Krueger, David and Torr, Philip and Barez, Fazl},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
}

@article{barez2025unlearning,
  category = {Safety},
  title = {Open Problems in Machine Unlearning for AI Safety},
  author = {Barez, Fazl and Fu, Tingchen and Prabhu, Ameya and Casper, Stephen and Sanyal, Amartya and Bibi, Adel and O'Gara, Aidan and Kirk, Robert and Bucknall, Ben and Fist, Tim and Ong, Luke and Torr, Philip and Lam, Kwok-Yan and Trager, Robert and Krueger, David and Mindermann, S{\"o}ren and Hernandez-Orallo, Jos{\'e} and Geva, Mor and Gal, Yarin},
  journal = {Under review},
  year = {2025},
}

@inproceedings{fu2025poisonbench,
  category = {Safety},
  title = {PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning},
  author = {Fu, Tingchen and Sharma, Mrinank and Torr, Philip and Cohen, Shay B. and Krueger, David and Barez, Fazl},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
}

@inproceedings{lo2024relearn,
  category = {Safety},
  title = {Large Language Models Relearn Removed Concepts},
  author = {Lo, Michelle and Cohen, Shay B. and Barez, Fazl},
  booktitle = {Annual Meeting of the Association for Computational Linguistics (ACL)},
  year = {2024},
}

@article{barez2026auditingagenda,
  category = {Governance},
  title = {Automated Interpretability-Driven Model Auditing and Control: A Research Agenda},
  author = {Barez, Fazl},
  journal = {AI Governance Initiative, Oxford Martin School, University of Oxford},
  year = {2026},
}

@article{barez2024safeguardingfinance,
  category = {Governance},
  title = {Safeguarding AI in Finance: Lessons for Regulated Industries},
  author = {Barez, Fazl and Marks, Luke},
  journal = {SSRN Working Paper 4937924},
  year = {2024},
}

@article{sania2026autocracies,
  category = {Society},
  title = {From Democracies to Autocracies: How AI Systems Enable Authoritarianism by Design},
  author = {Sania, Jakaria and Ziosi, Marta and Barez, Fazl},
  journal = {Under review},
  year = {2026},
}

@article{barez2025authoritarianism,
  category = {Society},
  title = {Toward Resisting AI-Enabled Authoritarianism},
  author = {Barez, Fazl and Friend, Isaac and Reid, Keir and Krawczuk, Igor and Wang, Vincent and M{\"o}kander, Jakob and Torr, Philip and Morse, Julia and Trager, Robert},
  journal = {Under review},
  year = {2025},
}

@article{gupta2025valbench,
  category = {Society},
  title = {VAL-Bench: Measuring Value Alignment in Language Models},
  author = {Gupta, Aman and O'Shea, Daniel and Barez, Fazl},
  journal = {Under review},
  year = {2025},
}