APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation
APCD:自适应路径对比解码用于可靠的大型语言模型生成
专题命中 其他推理 :reasoning(abstract);分类 cs.CL、cs.AI
AI总结 本文提出了一种自适应路径对比解码方法,通过自适应探索和受控路径交互提高大型语言模型生成的可靠性,实验表明在保持解码效率的同时提升了事实准确性。
Comments This paper has been withdrawn by the author to resolve a conflict of interest/compliance issue