RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions

arXiv:2402.16431v1 Announce Type: new
Abstract: Large Language Models (LLMs) have showcased remarkable capabilities in following human instructions. However, recent studies have raised concerns about the robustness of LLMs when prompted with instructions combining textual adversarial samples. In this paper, drawing inspiration from recent works that LLMs are sensitive to the design of the instructions, we utilize instructions in code style, which are more structural and less ambiguous, to replace typically natural language instructions. Through this conversion, we provide LLMs with …

abstract adversarial arxiv capabilities code concerns cs.cl human inspiration language language models large language large language models llms paper robustness samples studies style textual through type