Fetching the paper…

Reading the bibliography…

2021

Persistent Anti-Muslim Bias in Large Language Models

Abid, Abubakar, Farooqi, Maheen, Zou, James

Original
PDF
Post on X

Understand

It has been observed that large-scale language models capture undesirable societal biases, e.g.

relating to race and gender; yet religious bias has been relatively unexplored.
We demonstrate that GPT-3, a state-of-the-art contextual language model, captures persistent Muslim-violence bias.
We probe GPT-3 in various ways, including prompt completion, analogical reasoning, and story generation, to understand this anti-Muslim bias, demonstrating that it appears consistently and creatively in different uses of the model and that it is severe even compared to biases about other religious groups.

Persistent Anti-Muslim Bias in Large Language Models · Around

Built on

P. D. Turney, M. L. Littman, J. Bigham, V. Shnayder, arXiv preprint cs/0309035
2003
Earlier work this paper cites.
T. Mikolov, K. Chen, G. Corrado, J. Dean, arXiv preprint arXiv:1301.3781
Original
2013
Earlier work this paper cites.
A. M. Dai, Q. V. Le, Advances in neural information processing systems
2015
Earlier work this paper cites.
T. Bolukbasi, K.-W. Chang, J. Y. Zou, V. Saligrama, A. T. Kalai, Advances in neural information processing systems
2016
Earlier work this paper cites.
A. Vaswani, et al
2017
Earlier work this paper cites.

Similar

S. J. Rennie, E. Marcheret, Y. Mroueh, J. Ross, V. Goel, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
2017
Cited alongside, same era.
E. Sheng, K.-W. Chang, P. Natarajan, N. Peng, arXiv preprint arXiv:1909.01326
Original
2019
Cited alongside, same era.
S. Bordia, S. R. Bowman, arXiv preprint arXiv:1904.03035
Original
2019
Cited alongside, same era.
A. Abid, et al
Original
2019
Cited alongside, same era.
E. Wallace, S. Feng, N. Kandpal, M. Gardner, S. Singh, arXiv preprint arXiv:1908.07125
Original
2019
Cited alongside, same era.

Then

T. B. Brown, et al
Original
2020
Later among the works it cites.
N. Kitaev, Ł. Kaiser, A. Levskaya, arXiv preprint arXiv:2001.04451
Original
2020
Later among the works it cites.
M. Nadeem, A. Bethke, S. Reddy, arXiv preprint arXiv:2004.09456
Original
2020
Later among the works it cites.
K. Lu, P. Mardziel, F. Wu, P. Amancharla, A. Datta, Logic, Language, and Security
2020
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…