← 返回论文库

Self-Consistency Improves Chain of Thought Reasoning in Language Models

Wang, Wei, et al. (Google) · 2022
L3.1 · LLM Agent Patterns & FrameworksICLR 2023#reasoning
CORE IDEA
同一 prompt 采样 N 次 CoT，选最多数答案。
L-ANCHOR · 为什么在这一层重要
inference-time aggregation
arXiv:2203.11171 ↗

相关论文

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
L3.12022
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
L3.12023
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
L3.12023
LATS: Language Agent Tree Search Unifies Reasoning, Acting, and Planning
L3.12023