04:00
2026-07-24
arxiv.org
artificial-intelligence
Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'Hallucinations
Researchers propose EAACD, an expert-aware adaptive contrast decoding method for mixture-of-experts (MoE) models, to mitigate hallucinations in large language models (LLMs). The method leverages distiβ¦