1 citations · 2 across the 8 of their papers we have counts for
4 papers · 1 filter
Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents
Carol Xuan Long
In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive…
ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
Atefeh Gilani, Sajani Vithana, Carol Xuan Long +3
Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into generated tokens that either flags LLM…
Predictive Churn with the Set of Good Models
Jamelle Watson-Daniels, Flavio du Pin Calmon, Alexander D'Amour +3
Issues can arise when research focused on fairness, transparency, or safety is conducted separately from research driven by practical deployment concerns and vice versa. This separ…
Arbitrariness Lies Beyond the Fairness-Accuracy Frontier
Carol Xuan Long, Hsiang Hsu, Wael Alghamdi +1
Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predicti…