6 papers
Domain-Shift-Aware Conformal Prediction for Large Language Models
Zhexiao Lin, Yuanyuan Li, Neeraj Sarna +2
Large language models have achieved impressive performance across diverse tasks. However, their tendency to produce overconfident and factually incorrect outputs, known as hallucin…
Counterfactually Fair Conformal Prediction
Ozgur Guldogan, Neeraj Sarna, Yuanyuan Li +1
While counterfactual fairness of point predictors is well studied, its extension to prediction sets--central to fair decision-making under uncertainty--remains underexplored. On th…
Copyright Infringement Risk Reduction via Chain-of-Thought and Task Instruction Prompting
Neeraj Sarna, Yuanyuan Li, Michael von Gablenz
Large scale text-to-image generation models can memorize and reproduce their training dataset. Since the training dataset often contains copyrighted material, reproduction of train…
Safer Prompts: Reducing Risks from Memorization in Visual Generative AI
Lena Reissinger, Yuanyuan Li, Anna-Carolina Haensch +1
Visual Generative AI models have demonstrated remarkable capability in generating high-quality images from user inputs like text prompts. However, because these models have billion…
Quantifying Correlations of Machine Learning Models
Yuanyuan Li, Neeraj Sarna, Yang Lin
Machine Learning models are being extensively used in safety critical applications where errors from these models could cause harm to the user. Such risks are amplified when multip…
An In-Depth Examination of Risk Assessment in Multi-Class Classification Algorithms
Disha Ghandwani, Neeraj Sarna, Yuanyuan Li +1
Advanced classification algorithms are being increasingly used in safety-critical applications like health-care, engineering, etc. In such applications, miss-classifications made b…