Emotion-Conditioned Text Generation through Automatic Prompt Optimization
This addresses the challenge of cost-effective conditional text generation for applications like emotion-driven content creation, though it is incremental as it adapts prompt learning to a new task.
The paper tackles the problem of generating text conditioned on emotions without expensive fine-tuning, by introducing an automatic prompt optimization method that improves macro-average F1 from 0.22 to 0.75 for emotion realization in event reports.
Conditional natural language generation methods often require either expensive fine-tuning or training a large language model from scratch. Both are unlikely to lead to good results without a substantial amount of data and computational resources. Prompt learning without changing the parameters of a large language model presents a promising alternative. It is a cost-effective approach, while still achieving competitive results. While this procedure is now established for zero- and few-shot text classification and structured prediction, it has received limited attention in conditional text generation. We present the first automatic prompt optimization approach for emotion-conditioned text generation with instruction-fine-tuned models. Our method uses an iterative optimization procedure that changes the prompt by adding, removing, or replacing tokens. As objective function, we only require a text classifier that measures the realization of the conditional variable in the generated text. We evaluate the method on emotion-conditioned text generation with a focus on event reports and compare it to manually designed prompts that also act as the seed for the optimization procedure. The optimized prompts achieve 0.75 macro-average F1 to fulfill the emotion condition in contrast to manually designed seed prompts with only 0.22 macro-average F1.