Tag: model calibration
Browse our exclusive articles!
QuantSightBench: Benchmarking LLM Forecasts with Prediction Intervals
QuantSightBench evaluates LLM quantitative forecasting using prediction intervals to improve accuracy and reliability in real-world decision-making.
Bayesian-LoRA: Probabilistic Adaptation for Large Language Models
Discover Bayesian-LoRA, a probabilistic low-rank adaptation method that improves calibration and uncertainty in large language models with minimal paramete...
Geometric Insights on ROC and Precision-Recall Curves
Explore the geometric analysis of ROC and Precision-Recall curves to optimize binary classifiers and improve decision thresholds effectively.
Calibration-Aware Policy Optimization Boosts LLM Reasoning
Discover how Calibration-Aware Policy Optimization (CAPO) improves reasoning accuracy and confidence in Large Language Models by addressing overconfidence...
VOLTA: Rethinking Auxiliary Losses in Deep Learning Calibration
Discover how VOLTA outperforms traditional UQ methods, proving auxiliary losses less effective for calibrated deep learning and OOD detection.