Подписаться
Satyapriya Krishna
Satyapriya Krishna
Harvard University
Подтвержден адрес электронной почты в домене g.harvard.edu - Главная страница
Название
Процитировано
Процитировано
Год
BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
J Dhamala, T Sun, V Kumar, S Krishna, Y Pruksachatkun, KW Chang, ...
ACM FAccT Conference 2021, 2021
2832021
The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
S Krishna, T Han, A Gu, J Pombra, S Jabbari, S Wu, H Lakkaraju
Transactions on Machine Learning Research, 2024, 2024
2022024
Openxai: Towards a transparent evaluation of model explanations
C Agarwal, S Krishna, E Saxena, M Pawelczyk, N Johnson, I Puri, M Zitnik, ...
Advances in neural information processing systems 35, 15784-15799, 2022
1352022
Explaining machine learning models with interactive natural language conversations using TalkToModel
D Slack, S Krishna, H Lakkaraju, S Singh
Nature Machine Intelligence, 1-11, 2023
67*2023
Rethinking Stability for Attribution-based Explanations
C Agarwal, N Johnson, M Pawelczyk, S Krishna, E Saxena, M Zitnik, ...
ICLR 2022 Workshop on PAIR^2Struct: Privacy, Accountability …, 2022
482022
Post Hoc Explanations of Language Models Can Improve Language Models
S Krishna, J Ma, D Slack, A Ghandeharioun, S Singh, H Lakkaraju
Advances in Neural Information Processing Systems, 2023 36, 2023
432023
Adept: Auto-encoder based differentially private text transformation
S Krishna, R Gupta, C Dupuy
Proceedings of the 16th Conference of the European Chapter of the …, 2021
422021
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
U Gupta, J Dhamala, V Kumar, A Verma, Y Pruksachatkun, S Krishna, ...
Findings of the Association for Computational Linguistics: ACL 2022, 2022
382022
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification
Y Pruksachatkun, S Krishna, J Dhamala, R Gupta, KW Chang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021
312021
Black-Box Access is Insufficient for Rigorous AI Audits
S Casper, C Ezell, C Siegmann, N Kolt, TL Curtis, B Bucknall, A Haupt, ...
ACM FAccT Conference 2024, 2024
262024
Are Large Language Models Post Hoc Explainers?
N Kroeger, D Ley, S Krishna, C Agarwal, H Lakkaraju
arXiv preprint arXiv:2310.05797, 2023
212023
Eagle and finch: Rwkv with matrix-valued states and dynamic recurrence
B Peng, D Goldstein, Q Anthony, A Albalak, E Alcaide, S Biderman, ...
arXiv preprint arXiv:2404.05892, 2024
162024
Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
S Krishna, J Ma, H Lakkaraju
The Fortieth International Conference on Machine Learning (ICML), 2023, 2023
92023
Measuring Fairness of Text Classifiers via Prediction Sensitivity
S Krishna, R Gupta, A Verma, J Dhamala, Y Pruksachatkun, KW Chang
Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022
82022
On the Intersection of Self-Correction and Trust in Language Models
S Krishna
arXiv preprint arXiv:2311.02801, 2023
52023
Towards Realistic Single-Task Continuous Learning Research for NER
J Payan, Y Merhav, H Xie, S Krishna, A Ramakrishna, M Sridhar, R Gupta
Findings of the Association for Computational Linguistics: EMNLP 2021, 2021
52021
Understanding the Effects of Iterative Prompting on Truthfulness
S Krishna, C Agarwal, H Lakkaraju
Forty-first International Conference on Machine Learning, 2024, 2024
42024
On the Trade-offs between Adversarial Robustness and Actionable Explanations
S Krishna, C Agarwal, H Lakkaraju
arXiv preprint arXiv:2309.16452, 2023
3*2023
Finetext: text classification via attention-based language model fine-tuning
Y Tao, S Gupta, S Krishna, X Zhou, O Majumder, V Khare
Amazon Machine Learning Conference (AMLC) 2020, 2019
32019
Towards classification parity across cohorts
A Patel, R Gupta, M Harakere, S Krishna, A Alok, P Liu
ML-IRL Workshop at ICLR 2020, 2020
22020
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–20