@inproceedings{saparkhan-etal-2026-self,
    title = "Self-Consistency from Only Two Samples: {C}o{T}{--}{P}o{T} Ensembling for Efficient {LLM} Reasoning",
    author = "Saparkhan, Raman  and
      Hawasly, Majd  and
      Parvez, Md Rizwan  and
      Raza, Mohammad",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1642/",
    pages = "32804--32839",
    ISBN = "979-8-89176-395-1",
    abstract = "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 strengths of two distinct modes of reasoning: Chain-of-Thought (CoT) and Program-of-Thought (PoT). We describe a general framework for combining these two forms of reasoning in self-consistency, as well as particular strategies for both full sampling and early-stopping. We show that CoT-PoT ensembling not only improves overall accuracy, but also drastically reduces the number of samples required for SC by a factor of 9.3x. In particular, the majority of tasks (78.6{\%}) can be addressed with only two samples, which has not been possible with any prior SC methods."
}