Recently, Instruction fine-tuning has risen to prominence as a potential method for enhancing the zero-shot capabilities of Large Language Models (LLMs) on novel tasks. This technique has shown an exceptional ability to boost the performance of moderately sized LLMs, sometimes even reaching performance levels comparable to those of much larger model variants. The focus is on the robustness of instruction-tuned LLMs to seen and unseen tasks. We conducted an exploration of six models including Alpaca, Vicuna, WizardLM, and Traditional Task-oriented Models(Flan-T5-XL/XXL, T0++) using real-world relation extraction datasets as case studies. We carried out a comprehensive evaluation of these instruction-following LLMs which have been tuned based on open-domain instructions and task-oriented instructions. The main discussion is their performance and robustness towards instructions. We have observed that in most cases, the model's performance in dealing with unfamiliar instructions tends to worsen significantly, and the robustness of the model for RE instructions deteriorates compared to QA. Further, we discovered that up until a certain parameter size threshold (3B), the performance of the FLAN-T5 model improves as the parameter count increases. The robustness of different scales of FLAN-T5 models to RE instruction is worse than the robustness to QA instruction.

翻译：近期，指令微调作为一种潜在方法，因其能增强大型语言模型（LLMs）在新任务上的零样本能力而备受关注。该技术在提升中等规模LLMs的性能方面展现出卓越能力，有时甚至能达到与更大规模模型变体相当的性能水平。本文聚焦于指令微调后的LLMs在已见任务和未见任务上的鲁棒性。我们以真实关系抽取数据集作为案例研究，对包括Alpaca、Vicuna、WizardLM和传统任务导向模型（Flan-T5-XL/XXL、T0++）在内的六种模型进行了探索。我们对这些基于开放域指令和任务导向指令微调后的指令遵循型LLMs开展了全面评估，主要讨论它们在指令方面的性能与鲁棒性。我们观察到，在大多数情况下，模型处理不熟悉指令的性能会显著恶化，且模型对关系抽取（RE）指令的鲁棒性相比于问答（QA）更差。此外，我们发现直到某个参数规模阈值（3B）之前，FLAN-T5模型的性能随参数数量增加而提升。不同规模的FLAN-T5模型对RE指令的鲁棒性均劣于对QA指令的鲁棒性。