BriefGPT.xyz
May, 2023
一步步采样：适应性一致性用于LLMs高效推理
Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning with LLMs
HTML
PDF
Pranjal Aggarwal, Aman Madaan, Yiming Yang, Mausam
TL;DR
本文介绍了一种新的自适应一致性技术，用于提高大型语言模型输出结果的正确性和降低采样成本，实验证明该技术能够将采样成本降低最多6倍并且保持高精度。
Abstract
A popular approach for improving the correctness of output from
large language models
(LLMs) is
self-consistency
- poll the LLM multiple times and output the most frequent solution. Existing
→