Publications
Collaborative Development of NLP Models
F Khani, MT Ribeiro
Advances in Neural Information Processing Systems (Neurips), 2023
[slides] [twitter summary] [blog]
Targeted Data Generation: Finding and Fixing Model Weaknesses
Z He, MT Ribeiro, F Khani
Association for Computational Linguistics (ACL), 2023
Masktune: Mitigating spurious correlations by forcing to explore
S Asgari*, A Khani*, F Khani*, A Gholami, L Tran, A Mahdavi Amiri, G Hamarneh
Advances in Neural Information Processing Systems (Neurips), 2022
[code and data] [twitter summary]
On the opportunities and risks of foundation models
R Bommasani, … , F Khani, …, P Liang
preprint, 2022
Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
F Khani, P Liang
ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2021
[code and data] [video] [blog post] [twitter summary]
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
SM Xie, A Kumar, R Jones, F Khani, T Ma, P Liang
International Conference on Learning Representations (ICLR), 2021
[code and data] [twitter summary]
Feature Noise Induces Loss Discrepancy Across Groups
F Khani, P Liang
International Conference on Machine Learning (ICML), 2020
[code and data] [sides]
Maximum weighted loss discrepancy
F Khani, A Raghunathan, P Liang
Safe Machine Learning Workshop at International Conference on Learning Representations (safeML-ICLR) , 2019
[slides] [poster]
Planning, Inference and Pragmatics in Sequential Language Games
F Khani, ND Goodman, P Liang
Transactions of the Association for Computational Linguistics (TACL), 2018
[code and data] [slides]
Unanimous prediction for 100% precision with application to learning semantic mappings
F Khani, M Rinard, P Liang
Association for Computational Linguistics (ACL), 2016
[poster] [code and data]
An algorithm for discovering clusters of different densities or shapes in noisy data sets
F Khani, MJ Hosseini, AA Abin, H Beigy
Proceedings of the 28th Annual ACM Symposium on Applied Computing, 2013
Theses
Learning precise partial semantic mappings via linear algebra
Master thesis, Massachusetts Institute of Technlogoy
Causes, Measurement, and Mitigation of Loss Discrepancy
Ph.D. thesis, Stanford University