| Do-not-answer: A dataset for evaluating safeguards in llms Y Wang, H Li, X Han, P Nakov, T Baldwin arXiv preprint arXiv:2308.13387, 2023 | 322* | 2023 |
| Jais and jais-chat: Arabic-centric foundation and instruction-tuned open generative large language models N Sengupta, SK Sahu, B Jia, S Katipomu, H Li, F Koto, W Marshall, ... arXiv preprint arXiv:2308.16149, 2023 | 186* | 2023 |
| Diverse adversaries for mitigating bias in training X Han, T Baldwin, T Cohn arXiv preprint arXiv:2101.10001, 2021 | 86 | 2021 |
| Balancing out bias: Achieving fairness through balanced training X Han, T Baldwin, T Cohn arXiv preprint arXiv:2109.08253, 2021 | 76* | 2021 |
| Evaluating debiasing techniques for intersectional biases S Subramanian, X Han, T Baldwin, T Cohn, L Frermann arXiv preprint arXiv:2109.10441, 2021 | 68 | 2021 |
| Against The Achilles' Heel: A Survey on Red Teaming for Generative Models L Lin, H Mu, Z Zhai, M Wang, Y Wang, R Wang, J Gao, Y Zhang, W Che, ... Journal of Artificial Intelligence Research 82, 687-775, 2025 | 53 | 2025 |
| Safety at scale: A comprehensive survey of large model safety X Ma, Y Gao, Y Wang, R Wang, X Wang, Y Sun, Y Ding, H Xu, Y Chen, ... arXiv preprint arXiv:2502.05206, 2025 | 52 | 2025 |
| Contrastive learning for fair representations A Shen, X Han, T Cohn, T Baldwin, L Frermann arXiv preprint arXiv:2109.10645, 2021 | 44 | 2021 |
| Learning from failure: Integrating negative examples when fine-tuning large language models as agents R Wang, H Li, X Han, Y Zhang, T Baldwin arXiv preprint arXiv:2402.11651, 2024 | 42 | 2024 |
| Optimising equal opportunity fairness in model training A Shen, X Han, T Cohn, T Baldwin, L Frermann arXiv preprint arXiv:2205.02393, 2022 | 39 | 2022 |
| Toolgen: Unified tool retrieval and calling via generation R Wang, X Han, L Ji, S Wang, T Baldwin, H Li arXiv preprint arXiv:2410.03439, 2024 | 36 | 2024 |
| FairLib: A unified framework for assessing and improving fairness X Han, A Shen, Y Li, L Frermann, T Baldwin, T Cohn Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022 | 30* | 2022 |
| A Chinese dataset for evaluating the safeguards in large language models Y Wang, Z Zhai, H Li, X Han, S Lin, Z Zhang, A Zhao, P Nakov, T Baldwin Findings of the Association for Computational Linguistics: ACL 2024, 3106-3119, 2024 | 28 | 2024 |
| Decoupling Adversarial Training for Fair NLP X Han, T Baldwin, T Cohn Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021 | 28 | 2021 |
| Does representational fairness imply empirical fairness? A Shen, X Han, T Cohn, T Baldwin, L Frermann Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022 …, 2022 | 25 | 2022 |
| Towards equal opportunity fairness through adversarial learning X Han, T Baldwin, T Cohn arXiv preprint arXiv:2203.06317, 2022 | 20 | 2022 |
| Loki: An open-source tool for fact verification H Li, X Han, H Wang, Y Wang, M Wang, R Xing, Y Geng, Z Zhai, P Nakov, ... Proceedings of the 31st International Conference on Computational …, 2025 | 17 | 2025 |
| Fair enough: Standardizing evaluation and model selection for fairness research in NLP X Han, T Baldwin, T Cohn arXiv preprint arXiv:2302.05711, 2023 | 17 | 2023 |
| Ailuminate: Introducing v1. 0 of the ai risk and reliability benchmark from mlcommons S Ghosh, H Frase, A Williams, S Luger, P Röttger, F Barez, S McGregor, ... arXiv preprint arXiv:2503.05731, 2025 | 15 | 2025 |
| Systematic evaluation of predictive fairness X Han, A Shen, T Cohn, T Baldwin, L Frermann arXiv preprint arXiv:2210.08758, 2022 | 14 | 2022 |
Timothy BaldwinMBZUAI and The University of MelbourneVerified email at unimelb.edu.au
