基于泊松过程的可水印多草稿投机采样

中文摘要 AI 辅助

大型语言模型（LLMs）在广泛的任务中取得了最先进的性能，这推动了部署中的两个重要方面：推理效率和输出来源验证，分别可以通过投机采样和水印技术来解决。然而，最近的研究表明，将这两个目标结合起来是高度非平凡的，甚至可能是不可行的。在这项工作中，我们开发了一种基于泊松过程的新型多草稿投机采样算法，改善了这一基本权衡的前沿。所提出的算法本身具有强大的采样效率，更有趣的是，它天然可水印：我们可以嵌入无偏水印，而不会降低投机接受率。此外，我们的算法基于一种精确的无需通信的列表耦合方案，该方案产生了一种草稿者不变性属性，对采样和水印都有益处。这是第一个多草稿、草稿者不变的投机采样方案，同时保持了水印强度和采样效率，我们通过实验验证了其在两个方面的强大性能。

英文摘要

Large language models (LLMs) have achieved state-of-the-art performance across a wide range of tasks, motivating two important aspects of deployment: inference efficiency and output provenance, which can be tackled by speculative sampling and watermarking, respectively. However, recent works have shown that combining these two goals is highly nontrivial and can be potentially impossible. In this work, we develop a novel multi-draft speculative sampling algorithm based on Poisson processes that improves the frontier of this fundamental trade-off. The proposed algorithm has strong sampling efficiency on its own and, more interestingly, is naturally watermarkable: we can embed an unbiased watermark without degrading speculative acceptance. Moreover, our algorithm is based on an exact list-coupling-without-communication scheme, which yields a drafter invariance property that benefits both sampling and watermarking. It is the first multi-draft, drafter-invariant speculative sampling scheme that maintains both watermark strength and sampling efficiency, and we experimentally verify its strong performance in both aspects.

发表机构

• Imperial College London（帝国理工学院）
• University of Washington（华盛顿大学）

机构由 AI 辅助整理，请以论文原文为准。