用提示工程控制AI文本情绪，省钱又高效。
Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts
- 用零样本、思维链等提示法引导AI生成特定情绪文本
- 少量人工示例的少样本提示效果最佳，优于微调
- 适合资源有限时快速实现情感可控的AI应用
大型语言模型（LLMs）为实现情感自适应的人机交互提供了新机遇，但主动控制其生成文本的情绪仍具挑战。本研究探索了提示工程在控制LLM生成文本情绪方面的潜力，提供了一种资源敏感且易用的替代方案。基于埃克曼的六种基本情绪（如喜悦、厌恶），我们采用gpt-3.5-turbo模型，对比了零样本、思维链提示与微调等方法。结果显示，提示工程能有效引导AI生成具有特定情绪的文本，尤其在数据受限场景下，是一种实用且低成本的替代方案。其中，使用人工撰写示例的少样本提示表现最优，可能得益于更具体的任务引导。研究为构建情感自适应AI系统提供了重要参考。
原文摘要 · Abstract (English)
The groundbreaking capabilities of Large Language Models (LLMs) offer new opportunities for enhancing human-computer interaction through emotion-adaptive Artificial Intelligence (AI). However, deliberately controlling the sentiment in these systems remains challenging. The present study investigates the potential of prompt engineering for controlling sentiment in LLM-generated text, providing a resource-sensitive and accessible alternative to existing methods. Using Ekman's six basic emotions (e.g., joy, disgust), we examine various prompting techniques, including Zero-Shot and Chain-of-Thought prompting using gpt-3.5-turbo, and compare it to fine-tuning. Our results indicate that prompt engineering effectively steers emotions in AI-generated texts, offering a practical and cost-effective alternative to fine-tuning, especially in data-constrained settings. In this regard, Few-Shot prompting with human-written examples was the most effective among other techniques, likely due to the additional task-specific guidance. The findings contribute valuable insights towards developing emotion-adaptive AI systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。