layer-cake-contrastive-decoding

【效率与协作】Improve factual accuracy in LLM generation through decoding-time layer-wise attention suppression. Selectively suppress attention to specific token types at their most influential transformer depths without training or model modifications. Use when you need to reduce hallucinations and improve factual correctness at inference time.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准