Folgen
Hannah Rose Kirk
Hannah Rose Kirk
University of Oxford
Bestätigte E-Mail-Adresse bei oii.ox.ac.uk - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Bias out-of-the-box: An empirical analysis of intersectional occupational biases in popular generative language models
HR Kirk, Y Jun, F Volpin, H Iqbal, E Benussi, F Dreyer, A Shtedritski, ...
Advances in neural information processing systems 34, 2611-2624, 2021
2162021
Auditing large language models: a three-layered approach
J Mökander, J Schuett, HR Kirk, L Floridi
AI and Ethics 4 (4), 1085-1115, 2024
2062024
The benefits, risks and bounds of personalizing the alignment of large language models to individuals
HR Kirk, B Vidgen, P Röttger, SA Hale
Nature Machine Intelligence, 1-10, 2024
173*2024
Semeval-2023 task 10: Explainable detection of online sexism
HR Kirk, W Yin, B Vidgen, P Röttger
arXiv preprint arXiv:2303.04222, 2023
1352023
Dataperf: Benchmarks for data-centric ai development
M Mazumder, C Banbury, X Yao, B Karlaš, W Gaviria Rojas, S Diamos, ...
Advances in Neural Information Processing Systems 36, 5320-5347, 2023
1332023
Xstest: A test suite for identifying exaggerated safety behaviours in large language models
P Röttger, HR Kirk, B Vidgen, G Attanasio, F Bianchi, D Hovy
arXiv preprint arXiv:2308.01263, 2023
1212023
A prompt array keeps the bias away: Debiasing vision-language models with adversarial learning
H Berg, SM Hall, Y Bhalgat, W Yang, HR Kirk, A Shtedritski, M Bain
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the …, 2022
1072022
Hatemoji: A test suite and adversarially-generated dataset for benchmarking and detecting emoji-based hate
HR Kirk, B Vidgen, P Röttger, T Thrush, SA Hale
Proceedings of the 2022 Conference of the North American Chapter of the …, 2021
632021
Handling and Presenting Harmful Text in NLP
HR Kirk, A Birhane, B Vidgen, L Derczynski
EMNLP Findings, 2022
49*2022
The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
HR Kirk, A Whitefield, P Röttger, A Bean, K Margatina, J Ciro, R Mosquera, ...
arXiv preprint arXiv:2404.16019, 2024
462024
Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements
C Borchers, DS Gala, B Gilburt, E Oravkin, W Bounsi, YM Asano, HR Kirk
Proceedings of the 4th workshop on gender bias in natural language …, 2022
462022
Political compass or spinning arrow? towards more meaningful evaluations for values and opinions in large language models
P Röttger, V Hofmann, V Pyatkin, M Hinck, HR Kirk, H Schütze, D Hovy
arXiv preprint arXiv:2402.16786, 2024
452024
The past, present and better future of feedback learning in large language models for subjective human preferences and values
HR Kirk, AM Bean, B Vidgen, P Röttger, SA Hale
arXiv preprint arXiv:2310.07629, 2023
352023
Assessing language model deployment with risk cards
L Derczynski, HR Kirk, V Balachandran, S Kumar, Y Tsvetkov, MR Leiser, ...
arXiv preprint arXiv:2303.18190, 2023
342023
Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset
HR Kirk, Y Jun, P Rauba, G Wachtel, R Li, X Bai, N Broestl, M Doff-Sotta, ...
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), 2021
342021
Introducing v0. 5 of the ai safety benchmark from mlcommons
B Vidgen, A Agrawal, AM Ahmed, V Akinwande, N Al-Nuaimi, N Alfaraj, ...
arXiv preprint arXiv:2404.12241, 2024
302024
Simplesafetytests: a test suite for identifying critical safety risks in large language models
B Vidgen, N Scherrer, HR Kirk, R Qian, A Kannappan, SA Hale, P Röttger
arXiv preprint arXiv:2311.08370, 2023
262023
Visogender: A dataset for benchmarking gender bias in image-text pronoun resolution
SM Hall, F Gonçalves Abrantes, H Zhu, G Sodunke, A Shtedritski, HR Kirk
Advances in Neural Information Processing Systems 36, 2024
242024
Casteist but not racist? quantifying disparities in large language model bias between india and the west
K Khandelwal, M Tonneau, AM Bean, HR Kirk, SA Hale
arXiv preprint arXiv:2309.08573, 2023
222023
Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
J Quaye, A Parrish, O Inel, C Rastogi, HR Kirk, M Kahng, E Van Liemt, ...
The 2024 ACM Conference on Fairness, Accountability, and Transparency, 388-406, 2024
21*2024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20