Publications (9)
Oracle-Efficient Differentially Private Learning with Public Data
Adam Block, Mark Bun, Rathin Desai +2
Due to statistical lower bounds on the learnability of many function classes under privacy constraints, there has been recent interest in leveraging public data to improve the perf…
A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms
Nil-Jana Akpinar, Manish Nagireddy, Logan Stapleton +4
Motivated by the growing importance of reducing unfairness in ML predictions, Fair-ML researchers have presented an extensive suite of algorithmic 'fairness-enhancing' remedies. Mo…
The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
Satyapriya Krishna, Tessa Han, Alex Gu +3
As various post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to develop a deeper understanding of…
AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection
Kai Hua, Steven Wu, Ge Zhang +1
Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervis…
Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality
Xiaoyuan Zhu, Kimberly Le Truong, Riccardo Fogliato +8
As LLMs are deployed in high-stakes settings, users must judge the correctness of individual responses, often relying on model-generated justifications such as reasoning chains or…
Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
Xiaoyu Wu, Yifei Pang, Terrance Liu +1
Tabular data synthesis using diffusion models has gained significant attention for its potential to balance data utility and privacy. However, existing privacy evaluations often re…
Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
Santiago Cortes-Gomez, Carlos Patiño, Yewon Byun +3
Interest has been growing in decision-focused machine learning methods which train models to account for how their predictions are used in downstream optimization problems. Doing s…
Predicting Language Models' Success at Zero-Shot Probabilistic Prediction
Kevin Ren, Santiago Cortes-Gomez, Carlos Miguel Patiño +7
Recent work has investigated the capabilities of large language models (LLMs) as zero-shot models for generating individual-level characteristics (e.g., to serve as risk models or…
BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
Shengyuan Hu, Neil Kale, Pratiksha Thaker +3
Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning invo…