AINeutralarXiv – CS AI · 9h ago6/10
🧠
Geometry-Aware Hallucination Detection in Large Language Models
Researchers introduce GA-ICL, a geometry-aware framework that improves hallucination detection in large language models by selecting better in-context learning demonstrations. Rather than relying on surface-level text similarity, the method uses latent representations and prototype geometry to choose demonstrations, achieving stronger performance across factual verification and hallucination detection benchmarks while maintaining robustness across model scales.