RoMe: A Robust Metric for Evaluating Natural Language Generation. In Smaranda Muresan, Preslav Nakov, und Aline Villavicencio (Hrsg.), Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 5645--5657, Association for Computational Linguistics, Dublin, Ireland, Mai 2022. [PUMA: Evaluating Generation Language Metric Natural Robust Xack] URL
A human-machine collaborative framework for evaluating malevolence in dialogues. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 5612--5623, 2021. [PUMA: Zno collaborative evaluating framework human-machine malevolence]
Stable bias: evaluating societal representations in diffusion models. Proceedings of the 37th International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, USA, 2024. [PUMA: Stable bias diffusion evaluating imported models representations societal yaff]