Emotion-Conditioned Text Generation through Automatic Prompt Optimization
Menchaca Resendiz, Yarik; Klinger, Roman (2024): Emotion-Conditioned Text Generation through Automatic Prompt Optimization, in: Bamberg: Otto-Friedrich-Universität, S. 24–30.
Details
- Faculty/Chair
- Faculty/Professorship
- Author
- Menchaca Resendiz, Yarik
- Publisher Information
- Otto-Friedrich-Universität : Bamberg
- Year of publication
- 2024
- Source/Other editions
- Proceedings of the 1st Workshop on Taming Large Language Models : Controllability in the era of Interactive Assistants! / Devamanyu Hazarika, Xiangru Robert Tang, Di Jin (Hg.). - Prag : Association for Computational Linguistics, 2023, S. 24–30.
- Year of first publication
- 2023
- Language
- English
- Licence
- URN
- Abstract
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.
- GND Keywords
- Maschinelles LernenGenerierung <Sprache>GefühlPrompt Engineering
- Keywords
- Emotion-Conditioned Text Generation
- DDC Classification
- 004 Computer science
- RVK Classification
- ST 306
- Peer Reviewed
- yes
- International Distribution
- yes
- Open Access Journal
- yes
- Type
- Conferenceobject
- URI
- Activation date
- 2024-06-20
- Project(s)