EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Consistency-Constrained Self-Refinement for Multi-Step Mathematical Reasoning in Large Language Models

Baptiste Roux, Camille Perrin

INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES · 17.09.2026 · 6 (2) · 152-164

DOI: 10.66238/ijrss.v6i2.135 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES, online erschienen am 17.09.2026. Verfasst von Baptiste Roux und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models have demonstrated remarkable capabilities in natural language understanding and generation, yet their performance on complex, multi-step mathematical reasoning remains sub-optimal due to compounding errors and logical inconsistencies. This paper introduces a novel framework, Consistency-Constrained Self-Refinement, designed to enhance the mathematical problem-solving proficiency of language models. By integrating an iterative self-correction mechanism grounded in strict mathematical consistency constraints, the proposed architecture significantly reduces intermediate reasoning deviations. We formalize the verification process using algebraic invariants and logical consistency checks, ensuring that each generated reasoning step adheres to global constraints before proceeding to the subsequent state. Comprehensive experiments conducted on standardized mathematical reasoning benchmarks reveal substantial improvements in both accuracy and reasoning robustness compared to traditional chain-of-thought prompting and unconstrained self-reflection methods. The findings underscore the critical role of hard constraints in guiding the self-refinement trajectory of autoregressive language models. This research contributes to the broader objective of developing reliable, interpretable, and mathematically sound artificial intelligence systems capable of autonomous logical deduction.

Zitieren

APA

Roux, B., & Perrin, C. (2026). Consistency-Constrained Self-Refinement for Multi-Step Mathematical Reasoning in Large Language Models. INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES, 6(2), 152-164. https://doi.org/10.66238/ijrss.v6i2.135

Vancouver

Roux B, Perrin C. Consistency-Constrained Self-Refinement for Multi-Step Mathematical Reasoning in Large Language Models. INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES. 2026;6(2):152-164. doi:10.66238/ijrss.v6i2.135

BibTeX
@article{Roux2026,
  author = {Roux, Baptiste and Perrin, Camille},
  title = {Consistency-Constrained Self-Refinement for Multi-Step Mathematical Reasoning in Large Language Models},
  journal = {INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {152--164},
  doi = {10.66238/ijrss.v6i2.135}
}
Kostenlos starten →