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

arXiv: https://arxiv.org/abs/2609.30849 · HTML: https://mlsanity.com/paper/2609.30849/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 9 of 9)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behavior](https://mlsanity.com/paper/2006.01912/) (2020)
- [A Survey on Data Contamination for Large Language Models](https://mlsanity.com/paper/2502.14425/) (2025)
- [Noiser: Bounded Input Perturbations for Attributing Large Language Models](https://mlsanity.com/paper/2504.02911/) (2025)

## Abstract (arXiv)

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.