评估用于AI生成文本情感控制的提示工程策略
Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts
AI总结：
本文通过提示工程策略有效控制AI生成文本情感，相较于微调方法更具成本效益和实用性，尤其在数据受限环境下表现突出。
摘要：
大语言模型（LLMs）突破性的能力为通过情感适应性人工智能（AI）增强人机交互提供了新机会。然而，有意控制这些系统中的情感仍具挑战性。本研究探讨了提示工程在控制LLM生成文本情感方面的潜力，提供了一种资源敏感且易于获取的替代现有方法。使用Ekman的六种基本情绪（如喜悦、厌恶），我们检验了各种提示技术，包括使用gpt-3.5-turbo的零样本和思维链提示，以及与微调进行比较。我们的结果表明，提示工程能有效引导AI生成文本中的情感，提供了一种实用且成本效益高的替代微调方法，特别是在数据受限的环境中。在这方面，使用人工写作示例的Few-Shot提示在其他技术中最为有效，可能是因为额外的任务特定指导。这些发现为开发情感适应性AI系统提供了有价值的见解。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
