LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding

方法与贡献

对并行草稿的 top-K 候选计算相邻兼容性，再通过低开销的贪心路径选择得到草稿。

采用“候选—边—路径”结构，并使用针对投机解码前缀接受目标的局部训练与推断。

结合主题阅读

结构化解码：高阶 CRF、扩散语言模型与候选格 →

引用

Matan Rusanovsky, Yoav Miron, Roy Uziel, Omer Belhasin, Hao Guo, Ran Zilberstein, Maor Ashkenazi, Michael Elad. LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding. arXiv 2026.

@misc{rusanovsky2026lilicorr,
  title = {{LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding}},
  author = {Rusanovsky, Matan and Miron, Yoav and Uziel, Roy and Belhasin, Omer and Guo, Hao and Zilberstein, Ran and Ashkenazi, Maor and Elad, Michael},
  year = {2026},
  url = {https://arxiv.org/abs/2608.20530},
  eprint = {2608.20530},
  archivePrefix = {arXiv}
}