Verified75% confidenceFactExact time
Self-Consistency was proposed by Wang et al., selecting the most consistent answer by generating multiple reasoning paths and then using majority voting.
3
Sources
75%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSelf-consistency prompting has the model first output a reasoning chain before aggregating an answer; research shows this is more stable on edge cases than direct majority voting.76% similarUnverifiedSelf-Consistency方法由Wang等人2022年提出，在数学推理、代码生成等任务上展现出显著准确率提升73% similarUnverifiedSelf-consistency typically samples 3-5 reasoning paths and takes a majority vote; the cost is several times that of a single call, and it is suitable for math and logic problems with a unique correct answer.72% similarVerifiedSelf-Consistency was formally proposed by Google Research in the 2022 paper 'Self-Consistency Improves Chain of Thought Reasoning in Language Models.'62% similarUnverifiedSome research has proposed confidence-based adaptive stopping strategies that allow the model to autonomously determine when reasoning is complete.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/817492API
curl https://kongchang.com/api/v1/knowledge/claims/817492MCP
get_claim(id=817492)