#prompting-strategy News & Analysis

Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks

Researchers propose Robustness of Prompting (RoP), a novel prompting strategy that enhances Large Language Models' resilience against adversarial perturbations like typos and character errors. The two-stage approach combines error correction with guided inference, demonstrating significant improvements in robustness across arithmetic, commonsense, and logical reasoning tasks while maintaining accuracy on clean inputs.