This study investigates the use of prompt engineering to enhance large language models (LLMs), specifically GPT-4o-mini and gemini-1.5-flash, in sentiment analysis tasks. It evaluates advanced prompting techniques like few-shot learning, chain-of-thought prompting, and self-consistency against a baseline. Key tasks include sentiment classification, aspect-based sentiment analysis, and detecting subtle nuances such as irony. The research details the theoretical background, datasets, and methods used, assessing performance of LLMs as measured by accuracy, recall, precision, and F1 score. Findings reveal that advanced prompting significantly improves sentiment analysis, with the few-shot approach excelling in GPT-4o-mini and chain-of-thought prompting boosting irony detection in gemini-1.5-flash by up to 46%. Thus, while advanced prompting techniques overall improve performance, the fact that few-shot prompting works best for GPT-4o-mini and chain-of-thought excels in gemini-1.5-flash for irony detection suggests that prompting strategies must be tailored to both the model and the task. This highlights the importance of aligning prompt design with both the LLM's architecture and the semantic complexity of the task.

翻译：本研究探讨了利用提示工程增强大语言模型（LLMs），特别是GPT-4o-mini与gemini-1.5-flash，在情感分析任务中的表现。研究评估了少样本学习、思维链提示和自洽性等先进提示技术相对于基线的效果。核心任务包括情感分类、基于方面的情感分析以及反讽等微妙语义的检测。研究详细阐述了理论背景、数据集与使用方法，并通过准确率、召回率、精确率和F1分数评估了大语言模型的性能。研究结果表明，先进提示技术能显著提升情感分析效果：少样本方法在GPT-4o-mini中表现最优，而思维链提示使gemini-1.5-flash的反讽检测性能提升高达46%。由此可见，虽然先进提示技术整体上提升了模型性能，但少样本提示在GPT-4o-mini中效果最佳，而思维链提示在gemini-1.5-flash的反讽检测中表现突出，这表明提示策略需根据具体模型与任务进行定制。这凸显了提示设计必须与大语言模型的架构及任务的语义复杂性相匹配的重要性。