AI RESEARCH
Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
arXiv CS.AI
•
ArXi:2603.03332v2 Announce Type: replace-cross 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: \textit{MathError, UnitConversion, Sycophancy, SkippedSteps,} and \textit{ExtraSteps.