Get started
Author

Satyapriya Krishna

Observed name: Krishna, Satyapriya
ORCID: 0000-0002-5324-5824
Observed ORCID: 0000-0002-5324-5824
OpenAlex ID: A5114026120
Black-Box Access is Insufficient for Rigorous AI Audits
2024 · Stephen Casper, Carson Ezell, et al. · 79
A benchmark of expert-level academic questions to assess AI capabilities
2026 · Long Phan, Alice Gatti, et al. · Nature · 61
PDF
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
2022 · Umang Gupta, Jwala Dhamala, et al. · Findings of the Association for Computational Linguistics: ACL 2022 · 28
PDF
ADePT: Auto-encoder based Differentially Private Text Transformation
2021 · Satyapriya Krishna, Rahul Gupta, et al. · 24
PDF
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification
2021 · Yada Pruksachatkun, Satyapriya Krishna, et al. · 14
PDF
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
2024 · Peng, Bo, Goldstein, Daniel, et al. · arXiv (Cornell University) · 13
PDF
TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations
2022 · Slack, Dylan, Krishna, Satyapriya, et al. · arXiv (Cornell University) · 7
PDF
In-Context Explainers: Harnessing LLMs for Explaining Black Box Models
2023 · Kroeger, Nicholas, Ley, Dan, et al. · arXiv (Cornell University) · 6
PDF
Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
2023 · Krishna, Satyapriya, Ma, Jiaqi, et al. · arXiv (Cornell University) · 6
PDF
Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)
2024 · Verma, Apurv, Krishna, Satyapriya, et al. · arXiv (Cornell University) · 5
PDF
Understanding the Effects of Iterative Prompting on Truthfulness
2024 · Krishna, Satyapriya, Agarwal, Chirag, et al. · arXiv (Cornell University) · 4
PDF
Towards Realistic Single-Task Continuous Learning Research for NER
2021 · Justin Payan, Yuval Merhav, et al. · 4
PDF
FineText: Text Classification via Attention-based Language Model Fine-tuning
2019 · Tao, Yunzhe, Gupta, Saurabh, et al. · arXiv (Cornell University) · 4
PDF
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
2022 · Gupta, Umang, Dhamala, Jwala, et al. · arXiv (Cornell University) · 2
PDF
On the Trade-offs between Adversarial Robustness and Actionable Explanations
2024 · Satyapriya Krishna, Chirag Agarwal, et al. · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · 1
PDF
Post Hoc Explanations of Language Models Can Improve Language Models
2023 · Satyapriya Krishna, Jiaqi Ma, et al. · neural information processing systems · 1
Towards classification parity across cohorts
2020 · Patel, Aarsh, Gupta, Rahul, et al. · arXiv (Cornell University) · 1
PDF
TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue
2026 · Jiang, Freeman, Sanabria, Ramon, et al. · arXiv (Cornell University)
PDF
A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models
2026 · Gupta, Rahul, Mohanty, Abhinav, et al. · arXiv (Cornell University)
PDF
From Narrow Unlearning to Emergent Misalignment in LLMs
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
AutoSUIT Bench - Automated Security UnIt Test Benchmark for LLM Coding
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
Next-Billion AI Index: The compass for AI utility and adoption in the global majority
2026 · Rawat, Ambrish, He, Jessica, et al. · arXiv (Cornell University)
PDF
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
2026 · Liang, Jiacheng, Ma, Yao, et al. · arXiv (Cornell University)
Evaluating Nova 2.0 Lite model under Amazon's Frontier Model Safety Framework
2026 · Krishna, Satyapriya, Memelli, Matteo, et al. · arXiv (Cornell University)
PDF
Works count: 38
Citation count: 260
H-index: 7
I10-index: 6
Year
Topic
Type