Zachary C. Lipton

Carnegie Mellon University — United States

Computer Science · Physical Sciences

45h-index10.2kcitations263works3.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Topic Modeling(70), Natural Language Processing Techniques(40), Domain Adaptation and Few-Shot Learning(30), Adversarial Robustness in Machine Learning(24), Machine Learning and Data Classification(23)

Publications263 total

Valid Inference with Imperfect Synthetic Data
arXiv (Cornell University)·2025Open Access
OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
arXiv (Cornell University)·2025Open Access
No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference
arXiv (Cornell University)·2025Open Access
AI as an intervention: improving clinical outcomes relies on a causal approach to AI development and validation
Journal of the American Medical Informatics Association·2025· 13 citedOpen Access
Expert Routing with Synthetic Data for Continual Learning
arXiv (Cornell University)·2024Open Access
The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models
arXiv (Cornell University)·2024Open Access
Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
arXiv (Cornell University)·2024· 1 citedOpen Access
Online Data Collection for Efficient Semiparametric Inference
arXiv (Cornell University)·2024Open Access
Failure Modes of LLMs for Causal Reasoning on Narratives
arXiv (Cornell University)·2024· 1 citedOpen Access
Red-Teaming for Generative AI: Silver Bullet or Security Theater?
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2024· 47 citedOpen Access
Towards characterizing the value of edge embeddings in Graph Neural Networks
arXiv (Cornell University)·2024Open Access
The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
arXiv (Cornell University)·2024Open Access
A Unified Causal Framework for Auditing Recommender Systems for Ethical Concerns
arXiv (Cornell University)·2024Open Access
LLM-Select: Feature Selection with Large Language Models
arXiv (Cornell University)·2024· 7 citedOpen Access
Scaling Laws for Data Filtering—Data Curation Cannot be Compute Agnostic
2024· 9 cited
Position: Towards Bidirectional Human-AI Alignment
arXiv (Cornell University)·2024· 12 citedOpen Access
Understanding Hallucinations in Diffusion Models through Mode Interpolation
arXiv (Cornell University)·2024· 5 citedOpen Access
Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends
arXiv (Cornell University)·2024Open Access
The Impact of Differential Feature Under-reporting on Algorithmic Fairness
2024· 1 citedOpen Access
Rethinking LLM Memorization through the Lens of Adversarial Compression
arXiv (Cornell University)·2024Open Access
page 1 of 14Next →

Frequent Co-authors

Anima Anandkumar(6), Charles Elkan(5), Tommaso Furlanello(4), Jianfeng Gao(4), Li Deng(4), David C. Kale(3), Randall C. Wetzel(3), Yanyao Shen(3), Hyokun Yun(3), Yakov Kronrod(3), Animashree Anandkumar(3), Haohan Wang(3), Eric P. Xing(3), Bhuwan Dhingra(3), Divyansh Kaushik(3), Jean Kossaifi(3), Aran Khanna(3), Xiujun Li(3), Lihong Li(3), Michael Tschannen(2)