Verifying Large Language Models’ Reasoning Paths via Correlation Matrix Rank
Published in arXiv preprint arXiv:2510.24299, 2025
This work studies whether a model’s internal behavior can indicate the credibility of its own reasoning. It introduces Self-Indicator, a plug-and-play method that uses the rank of a correlation matrix between a problem and a generated reasoning path to reweight candidate solutions.
Recommended citation: Liu, J., Dai, W., Huang, Z., Miao, N., & Chen, E. (2025). "Verifying Large Language Models’ Reasoning Paths via Correlation Matrix Rank." arXiv preprint arXiv:2510.24299.
Download Paper