ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving

ArXi:2501.08203v3 Announce Type: replace While Large Language Models (LLMs) have shown impressive capabilities in math problem-solving tasks, their robustness to noisy inputs is not well-studied. We propose ArithmAttack to examine how robust the LLMs are when they encounter noisy prompts that contain extra noise in the form of punctuation marks. While being easy to implement, ArithmAttack does not cause any information loss since words are not added or deleted from the context.