Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913045290156032 |
|---|---|
| author | Saparkhan, Raman Hawasly, Majd Parvez, Md Rizwan Raza, Mohammad |
| author_facet | Saparkhan, Raman Hawasly, Majd Parvez, Md Rizwan Raza, Mohammad |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17433 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning Saparkhan, Raman Hawasly, Majd Parvez, Md Rizwan Raza, Mohammad Computation and Language Artificial Intelligence Machine Learning I.2.7 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. |
| title | Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning |
| topic | Computation and Language Artificial Intelligence Machine Learning I.2.7 |
| url | https://arxiv.org/abs/2604.17433 |