Instruction-tuned Large Language Models (LLMs) have exhibited impressive language understanding and the capacity to generate responses that follow specific instructions. However, due to the computational demands associated with training these models, their applications often rely on zero-shot settings. In this paper, we evaluate the zero-shot performance of two publicly accessible LLMs, ChatGPT and OpenAssistant, in the context of Computational Social Science classification tasks, while also investigating the effects of various prompting strategies. Our experiment considers the impact of prompt complexity, including the effect of incorporating label definitions into the prompt, using synonyms for label names, and the influence of integrating past memories during the foundation model training. The findings indicate that in a zero-shot setting, the current LLMs are unable to match the performance of smaller, fine-tuned baseline transformer models (such as BERT). Additionally, we find that different prompting strategies can significantly affect classification accuracy, with variations in accuracy and F1 scores exceeding 10%.

翻译：暂无翻译