Ninareh Mehrabi
Ninareh Mehrabi
Amazon Alexa AI
Verified email at - Homepage
Cited by
Cited by
A survey on bias and fairness in machine learning
N Mehrabi, F Morstatter, N Saxena, K Lerman, A Galstyan
ACM computing surveys (CSUR) 54 (6), 1-35, 2021
Exacerbating Algorithmic Bias through Fairness Attacks
N Mehrabi, M Naveed, F Morstatter, A Galstyan
Proceedings of the AAAI Conference on Artificial Intelligence, 2021
Man is to person as woman is to location: Measuring gender bias in named entity recognition
N Mehrabi, T Gowda, F Morstatter, N Peng, A Galstyan
Proceedings of the 31st ACM conference on Hypertext and Social Media, 231-232, 2020
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
N Mehrabi, P Zhou, F Morstatter, J Pujara, X Ren, A Galstyan
Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021
Dynamicgem: A library for dynamic graph embedding methods
P Goyal, SR Chhetri, N Mehrabi, E Ferrara, A Canedo
arXiv preprint arXiv:1811.10734, 2018
Debiasing community detection: the importance of lowly connected nodes
N Mehrabi, F Morstatter, N Peng, A Galstyan
Proceedings of the 2019 IEEE/ACM international conference on advances in …, 2019
Attributing fair decisions with attention interventions
N Mehrabi, U Gupta, F Morstatter, GV Steeg, A Galstyan
Proceedings of the 2nd Workshop on Trustworthy Natural Language Processing …, 2021
Flirt: Feedback loop in-context red teaming
N Mehrabi, P Goyal, C Dupuy, Q Hu, S Ghosh, R Zemel, KW Chang, ...
arXiv preprint arXiv:2308.04265, 2023
Robust Conversational Agents against Imperceptible Toxicity Triggers
N Mehrabi, A Beirami, F Morstatter, A Galstyan
Proceedings of the 2022 Conference of the North American Chapter of the …, 2022
Statistical equity: A fairness classification objective
N Mehrabi, Y Huang, F Morstatter
arXiv preprint arXiv:2005.07293, 2020
Is the elephant flying? resolving ambiguities in text-to-image generative models
N Mehrabi, P Goyal, A Verma, J Dhamala, V Kumar, Q Hu, KW Chang, ...
arXiv preprint arXiv:2211.12503, 2022
Towards multi-objective statistically fair federated learning
N Mehrabi, C de Lichy, J McKay, C He, W Campbell
arXiv preprint arXiv:2201.09917, 2022
The leaky pipeline in physics publishing
CO Ross, A Gupta, N Mehrabi, G Muric, K Lerman
arXiv preprint arXiv:2010.08912, 2020
Are you talking to ['xem'] or ['x','em']? On Tokenization and Addressing Misgendering in LLMs with Pronoun Tokenization Parity
A Ovalle, N Mehrabi, P Goyal, J Dhamala, KW Chang, R Zemel, ...
arXiv preprint arXiv:2312.11779, 2023
JAB: Joint adversarial prompting and belief augmentation
N Mehrabi, P Goyal, A Ramakrishna, J Dhamala, S Ghosh, R Zemel, ...
arXiv preprint arXiv:2311.09473, 2023
Where Does Bias in Common Sense Knowledge Models Come From?
S Melotte, F Ilievski, L Zhang, A Malte, N Mutha, F Morstatter, N Mehrabi
IEEE Internet Computing 26 (4), 12-20, 2022
On the steerability of large language models toward data-driven personas
J Li, N Mehrabi, C Peris, P Goyal, KW Chang, A Galstyan, R Zemel, ...
arXiv preprint arXiv:2311.04978, 2023
Tokenization matters: Navigating data-scarce tokenization for gender inclusive language technologies
A Ovalle, N Mehrabi, P Goyal, J Dhamala, KW Chang, R Zemel, ...
Findings of the Association for Computational Linguistics: NAACL 2024, 1739-1756, 2024
MICo: Preventative detoxification of large language models through inhibition control
R Siegelmann, N Mehrabi, P Goyal, P Goyal, L Bauer, J Dhamala, ...
Findings of the Association for Computational Linguistics: NAACL 2024, 1696-1703, 2024
Prompt perturbation consistency learning for robust language models
Y Qiang, S Nandi, N Mehrabi, GV Steeg, A Kumar, A Rumshisky, ...
arXiv preprint arXiv:2402.15833, 2024
The system can't perform the operation now. Try again later.
Articles 1–20