| Typology of risks of generative text-to-image models C Bird, E Ungless, A Kasirzadeh Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 396-410, 2023 | 100 | 2023 |
| This prompt is measuring <mask>: evaluating bias evaluation in language models S Goldfarb-Tarrant, E Ungless, E Balkir, SL Blodgett Findings of the Association for Computational Linguistics: ACL 2023, 2023 | 31 | 2023 |
| A Robust Bias Mitigation procedure based on the stereotype content model EL Ungless, A Rafferty, H Nag, B Ross Proceedings of the Fifth Workshop on Natural Language Processing and …, 2022 | 26 | 2022 |
| Stereotypes and Smut: The (Mis) representation of Non-cisgender Identities by Text-to-Image Models EL Ungless, B Ross, A Lauscher Findings of the Association for Computational Linguistics: ACL 2023, 2023 | 24 | 2023 |
| Potential pitfalls with automatic sentiment analysis: The example of queerphobic bias EL Ungless, B Ross, V Belle Social science computer review 41 (6), 2211-2229, 2023 | 14 | 2023 |
| Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models EL Ungless, N Vitsakis, Z Talat, J Garforth, B Ross, A Onken, ... arXiv preprint arXiv:2410.19812, 2024 | 2 | 2024 |
| Just Because We Camp, Doesn't Mean We Should: The Ethics of Modelling Queer Voices A Sigurgeirsson, EL Ungless arXiv preprint arXiv:2406.07504, 2024 | 2 | 2024 |
| Experiences of censorship on TikTok across marginalised identities EL Ungless, N Markl, B Ross arXiv preprint arXiv:2407.14164, 2024 | 1 | 2024 |
| The Only Way is Ethics: A Guide to Ethical Research with Large Language Models EL Ungless, N Vitsakis, Z Talat, J Garforth, B Ross, A Onken, ... arXiv preprint arXiv:2412.16022, 2024 | | 2024 |
Björn RossUniversity of EdinburghE-mailová adresa ověřena na: ed.ac.uk