6 papers
Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
Carol Xuan Long, David Simchi-Levi, Feng Zhu +3
This paper studies autonomous generative AI agents in multi-echelon supply chains using the MIT Beer Game. We identify four inference-time levers that shape performance: model sele…
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…
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…
HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictions
Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun +5
Large language model (LLM) watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate b…
Optimized Couplings for Watermarking Large Language Models
Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun +3
Large-language models (LLMs) are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of water…
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…