Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection

ACL ARR 2025 February Submission5379 Authors

Abstract:

Large language models(LLMs) have demonstrated strong mathematical reasoning capabilities but remain susceptible to hallucinations—producing plausible yet incorrect statements—especially in theorem proving, symbolic manipulation ,and numerical computation.
While self-consistency(SC) has been explored as a means to improve factuality ,existing approaches primarily apply SC to final -answer
selection ,neglecting the ogical consistency of intermediate reasoning steps. So we introduce a structured self-consistency framework
designed to enhance the reliability of mathematical reasoning. Our method enforces self-consistency across intermediate steps and final
outputs ,reducing logical inconsistencies and hallucinations. Experimental results demonstrate that our SC significantly improves proof
validity ,symbolic reasoning accuracy, and numerical stability while maintaining computational efficiency. Further analysis reveals that
structured self-consistency not only enhances problem-solving accuracy but also reduces the variance of model generated outputs.These findings highlight self-consistency as a robust mechanism for improving mathematical reasoning in LLMs ,paving the way for more reliable
and interpretable AI-driven mathematics.

Paper Type: Long

Research Area: Language Modeling

Research Area Keywords: 1.Mathematical Reasoning 2.Large Language Models

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 5379