2 papers
cs.LG2026
Aligning Language Models with Selective Prediction
Gaoxiang Luo, Yifan Wu, Sinian Zhang +2
Large language models (LLMs) are increasingly deployed as critical decision-making components in high-stakes real-world AI systems, rendering LLM reliability a foremost practical c…
cs.LG2025
COM-BOM: Bayesian Exemplar Search for Efficiently Exploring the Accuracy-Calibration Pareto Frontier
Gaoxiang Luo, Aryan Deshwal
Selecting an optimal set of exemplars is critical for good performance of in-context learning. However, prior exemplar search methods narrowly optimize for predictive accuracy, cri…