Kush R. Varshney

IBM (United States) — United States

Social Sciences · Social Sciences

37h-index6.5kcitations275works3.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Ethics and Social Impacts of AI(47), Explainable Artificial Intelligence (XAI)(47), Adversarial Robustness in Machine Learning(21), Privacy-Preserving Technologies in Data(20), Machine Learning and Data Classification(19)

Publications275 total

Exposing AI Bias by Crowdsourcing: Democratizing Critique of Large Language Models
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2025· 1 citedOpen Access
CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions
arXiv (Cornell University)·2025· 2 citedOpen Access
The Ultimate Test of Superintelligent AI Agents: Can an AI Balance Care and Control in Asymmetric Relationships?
arXiv (Cornell University)·2025Open Access
When trust is zero sum: automation’s threat to epistemic agency
Ethics and Information Technology·2025· 3 cited
A Task-Driven Human-AI Collaboration: When to Automate, When to Collaborate, When to Challenge
arXiv (Cornell University)·2025Open Access
A Review of Copy-Move Image Forgery Detection
2025· 1 cited
Contextual Value Alignment
2025
Rethinking machine unlearning for large language models
UNC Libraries·2025Open Access
Rethinking machine unlearning for large language models
Nature Machine Intelligence·2025· 46 cited
Scopes of Alignment
arXiv (Cornell University)·2025Open Access
Granite Guardian: Comprehensive LLM Safeguarding
2025· 2 citedOpen Access
Evaluating the Prompt Steerability of Large Language Models
2025· 1 citedOpen Access
Granite Guardian
arXiv (Cornell University)·2024Open Access
Hey GPT, Can You be More Racist? Analysis from Crowdsourced Attempts to Elicit Biased Content from Generative AI
arXiv (Cornell University)·2024· 3 citedOpen Access
Racial and Neighborhood Disparities in Legal Financial Obligations in Jefferson County, Alabama
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2024Open Access
Decolonial AI Alignment: Openness, Visesa-Dharma, and Including Excluded Knowledges
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2024· 6 citedOpen Access
Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
arXiv (Cornell University)·2024Open Access
Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
IEEE Internet Computing·2024· 4 cited
Value Alignment from Unstructured Text
arXiv (Cornell University)·2024Open Access
When Trust is Zero Sum: Automation Threat to Epistemic Agency
arXiv (Cornell University)·2024Open Access
page 1 of 14Next →

Frequent Co-authors

Aleksandra Mojsilović(14), Dennis Wei(14), Prasanna Sattigeri(13), Karthikeyan Natesan Ramamurthy(12), Michael Hind(11), Rachel Bellamy(9), Samuel C. Hoffman(9), Stephanie Houde(9), Yunfeng Zhang(8), Amit Dhurandhar(8), John T. Richards(7), Moninder Singh(7), Sameep Mehta(6), Pranay Lohia(5), Diptikalyan Saha(5), Pin‐Yu Chen(5), Karthikeyan Shanmugam(5), Lav R. Varshney(5), Kuntal Dey(4), Kalapriya Kannan(4)