Preprint · 2025 · Open access
CC-LEARN: Cohort-based Consistency Learning
arXiv (Cornell University) · Published 18 June 2025 · DOI 10.48550/arxiv.2506.15662
In brief
“CC-LEARN: Cohort-based Consistency Learning” is a 2025 preprint by Xiao Ye and 8 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 3
- Most cited in
- 2026 (2)
- References
- 6
- Authors
- 9
Abstract
Large language models excel at many tasks but still struggle with consistent, robust reasoning. We introduce Cohort-based Consistency Learning (CC-Learn), a reinforcement learning framework that improves the reliability of LLM reasoning by training on cohorts of similar questions derived from shared programmatic abstractions. To enforce cohort-level consistency, we define a composite objective combining cohort accuracy, a retrieval bonus for effective problem decomposition, and a rejection penalty for trivial or invalid lookups that reinforcement learning can directly optimize, unlike supervised fine-tuning. Optimizing this reward guides the model to adopt uniform reasoning patterns across all cohort members. Experiments on challenging reasoning benchmarks (including ARC-Challenge and StrategyQA) show that CC-Learn boosts both accuracy and reasoning stability over pretrained and SFT baselines. These results demonstrate that cohort-level RL effectively enhances reasoning consistency in LLMs.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ye, X., Shaswat, S., Li, Z., Dineen, J., Lu, S., Ahuja, A., Shen, M., Xu, Z., & Zhou, B. Z. (2025). CC-LEARN: Cohort-based Consistency Learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.15662
MLA 9
Ye, Xiao, et al. “CC-LEARN: Cohort-based Consistency Learning.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2506.15662.
Chicago
Ye, Xiao, Shrivastava, Shaswat, Zhaonan Li, Jacob Dineen, Shijie Lu, Aryan Ahuja, Ming Shen, Zhikun Xu, and Ben Zhi Zhou. 2025. “CC-LEARN: Cohort-based Consistency Learning.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.15662.
Harvard
Ye, X. et al. (2025) ‘CC-LEARN: Cohort-based Consistency Learning’, arXiv (Cornell University). doi:10.48550/arxiv.2506.15662.
IEEE
X. Ye et al., “CC-LEARN: Cohort-based Consistency Learning,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2506.15662.
BibTeX
@misc{ye2025learn,
title = {{CC-LEARN: Cohort-based Consistency Learning}},
author = {Ye, Xiao and Shaswat, Shrivastava, and Li, Zhaonan and Dineen, Jacob and Lu, Shijie and Ahuja, Aryan and Shen, Ming and Xu, Zhikun and Zhou, Ben Zhi},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2506.15662},
url = {https://doi.org/10.48550/arxiv.2506.15662}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- large language models
- reasoning consistency
- reinforcement learning
- problem decomposition
- reasoning stability
- LLM fine-tuning
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Ye, X., Shaswat, S., Li, Z., Dineen, J., Lu, S., Ahuja, A., Shen, M., Xu, Z., & Zhou, B. Z. (2025). CC-LEARN: Cohort-based Consistency Learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.15662
How many times has this paper been cited?
3 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at arXiv (Cornell University).
Who wrote this paper?
Xiao Ye, Shrivastava, Shaswat, Zhaonan Li, Jacob Dineen, Shijie Lu, Aryan Ahuja, Ming Shen, Zhikun Xu, Ben Zhi Zhou.
What is the DOI of this paper?
10.48550/arxiv.2506.15662. The permanent link is https://doi.org/10.48550/arxiv.2506.15662.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.