Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations

arXiv:2603.03332v2 Announce Type: replace-cross
Abstract: Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly understood. This paper presents a comprehensive empirical evaluation of LLM robustness to a structured taxonomy of 5 CoT perturbation types: textitMathError, UnitConversion, Sycophancy, SkippedSteps, and textitExtraSteps. We evaluate 13 models spanning three orders of magnitude in parameter count (3B to 1.5TfootnoteAssumed parameter count of closed models), testing their ability to complete mathematical reasoning tasks despite perturbations injected at different points in the reasoning chain. Our key findings reveal heterogeneous vulnerability patterns: MathError perturbations produce the most severe degradation in small models (50-60% accuracy loss) but show strong scaling benefits; UnitConversion remains challenging across all scales (20-30% loss even for largest models); ExtraSteps incur minimal accuracy degradation (0-6%) regardless of scale; Sycophancy produces modest effects (7% loss for small models); and SkippedSteps cause intermediate damage (15% loss). Scaling relationships follow power-law patterns, with model size serving as a protective factor against some perturbations but offering limited defense against dimensional reasoning tasks. These findings have direct implications for deploying LLMs in multi-stage reasoning pipelines and underscore the necessity of task-specific robustness assessments and mitigation strategies. The code and results are available https://github.com/Mystic-Slice/CoTPerturbation.