Tolga Bolukbasi
Cited by
Cited by
Man is to computer programmer as woman is to homemaker? debiasing word embeddings
T Bolukbasi, KW Chang, JY Zou, V Saligrama, AT Kalai
Advances in neural information processing systems 29, 2016
The what-if tool: Interactive probing of machine learning models
J Wexler, M Pushkarna, T Bolukbasi, M Wattenberg, F Viégas, J Wilson
IEEE transactions on visualization and computer graphics 26 (1), 56-65, 2019
Adaptive neural networks for efficient inference
T Bolukbasi, J Wang, O Dekel, V Saligrama
International Conference on Machine Learning, 527-536, 2017
Xrai: Better attributions through regions
A Kapishnikov, T Bolukbasi, F Viégas, M Terry
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
The language interpretability tool: Extensible, interactive visualizations and analysis for NLP models
I Tenney, J Wexler, J Bastings, T Bolukbasi, A Coenen, S Gehrmann, ...
arXiv preprint arXiv:2008.05122, 2020
Quantifying and reducing stereotypes in word embeddings
T Bolukbasi, KW Chang, J Zou, V Saligrama, A Kalai
arXiv preprint arXiv:1606.06121, 2016
Debiasing embeddings for reduced gender bias in text classification
F Prost, N Thain, T Bolukbasi
arXiv preprint arXiv:1908.02810, 2019
Guided integrated gradients: An adaptive path method for removing noise
A Kapishnikov, S Venugopalan, B Avci, B Wedin, M Terry, T Bolukbasi
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021
Model selection by linear programming
J Wang, T Bolukbasi, K Trapeznikov, V Saligrama
Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland …, 2014
Bing++: A fast high quality object proposal generator at 100fps
Z Zhang, Y Liu, T Bolukbasi, MM Cheng, V Saligrama
arXiv preprint arXiv:1511.04511 1, 2015
An interpretability illusion for bert
T Bolukbasi, A Pearce, A Yuan, A Coenen, E Reif, F Viégas, ...
arXiv preprint arXiv:2104.07143, 2021
Tracing knowledge in language models back to the training data
E Akyürek, T Bolukbasi, F Liu, B Xiong, I Tenney, J Andreas, K Guu
arXiv preprint arXiv:2205.11482, 2022
Towards tracing knowledge in language models back to the training data
E Akyürek, T Bolukbasi, F Liu, B Xiong, I Tenney, J Andreas, K Guu
Findings of the Association for Computational Linguistics: EMNLP 2022, 2429-2446, 2022
Resource constrained structured prediction
T Bolukbasi, KW Chang, J Wang, V Saligrama
Proceedings of the AAAI Conference on Artificial Intelligence 31 (1), 2017
Simfluence: Modeling the influence of individual training examples by simulating training runs
K Guu, A Webson, E Pavlick, L Dixon, I Tenney, T Bolukbasi
arXiv preprint arXiv:2303.08114, 2023
Building a robust text classifier on a test-time budget
MR Parvez, T Bolukbasi, KW Chang, V Sarigrama
CoRR, abs, 1808
Towards Agile Text Classifiers for Everyone
M Mozes, J Hoffmann, K Tomanek, M Kouate, N Thain, A Yuan, ...
arXiv preprint arXiv:2302.06541, 2023
Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
M Mozes, T Bolukbasi, A Yuan, F Liu, N Thain, L Dixon
arXiv preprint arXiv:2302.06598, 2023
IMACS: Image Model Attribution Comparison Summaries
E Schoop, B Wedin, A Kapishnikov, T Bolukbasi, M Terry
arXiv preprint arXiv:2201.11196, 2022
Probing ML models for fairness with the what-if tool and SHAP: hands-on tutorial
J Wexler, M Pushkarna, S Robinson, T Bolukbasi, A Zaldivar
Proceedings of the 2020 Conference on Fairness, Accountability, and …, 2020
The system can't perform the operation now. Try again later.
Articles 1–20