一作ACL 2026Findings· Findings of ACL
Self-Consistency from Only Two Samples: C o T – P o T Ensembling for Efficient LLM Reasoning
Raman Saparkhan · Majd Hawasly · Md Rizwan Parvez · Mohammad Raza
摘要
Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling. We introduce a hybrid ensembling approach that leverages the complementary stren...