Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts
This addresses the challenge of sentiment control in AI systems for developers and users, but it is incremental as it builds on existing prompt engineering methods.
The study tackled controlling sentiment in AI-generated texts by evaluating prompt engineering strategies, finding that Few-Shot prompting with human-written examples was the most effective, offering a practical and cost-effective alternative to fine-tuning in data-constrained settings.
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.