Sangyeon Yu

You are already at the latest version Large language models, despite their strong performance, frequently produce hallucinated content by excessively relying on pre-trained knowledge and overlooking newly provided prompts. We introduce LACD, a technique that dynamically rebalances probability distributions across layers, ensuring critical context is not overshadowed. By emphasizing new prompt information, LACD alleviates lower-layer dominance and mitigates hallucinations.