AIBullisharXiv – CS AI · Mar 37/104
🧠
HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
Researchers introduce HalluGuard, a new framework that identifies and addresses both data-driven and reasoning-driven hallucinations in Large Language Models. The system achieved state-of-the-art performance across 10 benchmarks and 9 LLM backbones, offering a unified approach to improve AI reliability in critical domains like healthcare and law.