AI RESEARCH
Boosting Self-Consistency with Ranking
arXiv CS.CL
•
ArXi:2606.05054v1 Announce Type: new Self-consistency improves large language models by sampling multiple reasoning paths and selecting the most frequent answer, but majority voting often fails to recover correct answers that are already present among the samples. We address this limitation with Ranking-Improved Self-Consistency (RISC), which reformulates answer selection in self-consistency as a ranking problem.