Hi and welcome! Thank you for visiting our website. You're in the right place!
This page is the supplementary material of our paper "Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models". You can explore detailed hallucination analysis results here, conducted using Grok 3.0. For each model, five independent responses were generated using test data and subsequently evaluated.
We hope you find this website insightful and engaging! 😃