Enhancing Assessment of Self-Consistency in LLM Explanations using Perturbation Strength

arXiv:2609.30849v1 Announce Type: new Abstract: Prior work has examined the self-consistency of LLM-generated explanations using surface-level perturbation methods. However, the strength of these perturbations is not explicitly measured and controlled. In this work, we propose an LLM-as-a-judge approach to measure perturbation strength in a unified manner across input and CoT perturbations. We then evaluate the self-consistency in explanations generated from various LLMs under controlled strength conditions, ensuring a fair comparison across perturbation types. Experiments show that our proposed LLM-based perturbation strength measure outperforms other embedding- and probability-based approaches and that input perturbations generally affect LLMs more strongly than CoT perturbations. Our work suggests that judgments about a model's self-consistency is fair only within the same perturbation type.

Related

• Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
• Self-Consistency via Marginal Sharpening
• CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency

Source: arXiv cs.CL | 2026-09-28