25 citations · 38 across the 18 of their papers we have counts for
19 papers
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
Peihan Liu, Lucas Rosenblatt, Weiwei Kong +7
Differentially private (DP) text synthesis promises to unlock sensitive corpora for model training, but it remains unclear whether DP synthetic data transmits genuinely new knowled…
Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation
Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar
As AI models progress beyond simple chatbots into more complex workflows, we draw ever closer to the event horizon beyond which AI systems will be utilized in autonomous, self-main…
Exactly Computing do-Shapley Values
R. Teal Witter, Álvaro Parafita, Tomas Garriga +4
Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapl…
Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data
Lucas Rosenblatt, Peihan Liu, Ryan McKenna +1
Research on differentially private synthetic tabular data has largely focused on independent and identically distributed rows where each record corresponds to a unique individual.…
Explanation Multiplicity in SHAP: Characterization and Assessment
Hyunseung Hwang, Seungeun Lee, Lucas Rosenblatt +2
SHAP explanations are widely used in high-stakes settings to justify decisions, yet they can differ substantially across repeated runs, even when the model, the input instance, and…
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
Natalia Ponomareva, Zheng Xu, H. Brendan McMahan +12
High quality data is needed to unlock the full potential of AI for end users. However finding new sources of such data is getting harder: most publicly-available human generated da…
SimKey: A Semantically Aware Key Module for Watermarking Language Models
Shingo Kodama, Haya Diwan, Lucas Rosenblatt +2
The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a…
We Are AI: Taking Control of Technology
Julia Stoyanovich, Armanda Lewis, Eric Corbett +3
Responsible AI (RAI) is the science and practice of ensuring the design, development, use, and oversight of AI are socially sustainable--benefiting diverse stakeholders while contr…
Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data
Shlomi Hod, Lucas Rosenblatt, Julia Stoyanovich
Differentially private (DP) machine learning often relies on the availability of public data for tasks like privacy-utility trade-off estimation, hyperparameter tuning, and pretrai…
Differential Privacy Under Class Imbalance: Methods and Empirical Insights
Lucas Rosenblatt, Yuliia Lut, Eitan Turok +2
Imbalanced learning occurs in classification settings where the distribution of class-labels is highly skewed in the training data, such as when predicting rare diseases or in frau…
FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness
Lucas Rosenblatt, R. Teal Witter
Fair predictive algorithms hinge on both equality and trust, yet inherent uncertainty in real-world data challenges our ability to make consistent, fair, and calibrated decisions.…
A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacy
Lucas Rosenblatt, Julia Stoyanovich, Christopher Musco
Differentially private (DP) mechanisms have been deployed in a variety of high-impact social settings (perhaps most notably by the U.S. Census). Since all DP mechanisms involve add…
I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives
R. Teal Witter, Lucas Rosenblatt
The open streets initiative "opens" streets to pedestrians and bicyclists by closing them to cars and trucks. The initiative, adopted by many cities across North America, increases…
The Possibility of Fairness: Revisiting the Impossibility Theorem in Practice
Andrew Bell, Lucius Bynum, Nazarii Drushchak +3
The ``impossibility theorem'' -- which is considered foundational in algorithmic fairness literature -- asserts that there must be trade-offs between common notions of fairness and…
Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI
Lorena Piedras, Lucas Rosenblatt, Julia Wilkins
Detecting "toxic" language in internet content is a pressing social and technical challenge. In this work, we focus on PERSPECTIVE from Jigsaw, a state-of-the-art tool that promise…
Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy
Lucas Rosenblatt, Bernease Herman, Anastasia Holovenko +7
Differential privacy (DP) data synthesizers support public release of sensitive information, offering theoretical guarantees for privacy but limited evidence of utility in practica…
Counterfactual Fairness Is Basically Demographic Parity
Lucas Rosenblatt, R. Teal Witter
Making fair decisions is crucial to ethically implementing machine learning algorithms in social settings. In this work, we consider the celebrated definition of counterfactual fai…
Spending Privacy Budget Fairly and Wisely
Lucas Rosenblatt, Joshua Allen, Julia Stoyanovich
Differentially private (DP) synthetic data generation is a practical method for improving access to data as a means to encourage productive partnerships. One issue inherent to DP i…
Differentially Private Synthetic Data: Applied Evaluations and Enhancements
Lucas Rosenblatt, Xiaoyan Liu, Samira Pouyanfar +3
Machine learning practitioners frequently seek to leverage the most informative available data, without violating the data owner's privacy, when building predictive models. Differe…