AIBullisharXiv – CS AI · 6h ago7/10
🧠
Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping
Researchers introduce DeLask, a novel decoding framework that reduces hallucinations in Large Language Models by dynamically skipping decoder layers prone to generating false information. The method uses gradient-based analysis to identify problematic layers and partially aggregates their hidden states, demonstrating consistent improvements across diverse LLMs without requiring model retraining.