AI Reliability

The Illusion of AI Expertise Under Uncertainty: Navigating Elusive Ground Truth via a Probabilistic Paradigm

Accounting for ambiguous ground truth when comparing AI systems with experts.

Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models

Detecting and reducing repetitive language patterns through sampling and targeted fine-tuning.

The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs

Reassessing hallucination detection with evaluation metrics that better reflect meaning.

Fine-Tuning with Uncertainty-Aware Priors Makes Vision and Language Foundation Models More Reliable

Improving the reliability of fine-tuned foundation models with priors that account for uncertainty.

Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation

Adjusting dropout during inference to estimate uncertainty without additional labels or training.