Emotion-Conditioned Text Generation through Automatic Prompt Optimization
Menchaca Resendiz, Yarik; Klinger, Roman (2023): Emotion-Conditioned Text Generation through Automatic Prompt Optimization, in: Devamanyu Hazarika, Xiangru Robert Tang, Di Jin, u. a. (Hrsg.), Proceedings of the 1st Workshop on Taming Large Language Models : Controllability in the era of Interactive Assistants!, Prag: Association for Computational Linguistics, S. 24–30.
Details
- Autorin(nen)/Autor(en)
- Menchaca Resendiz, Yarik
- Titel des Sammelwerks
- Proceedings of the 1st Workshop on Taming Large Language Models : Controllability in the era of Interactive Assistants!
- Herausgeberin(nen)/Herausgeber des Sammelwerks
- Hazarika, DevamanyuTang, Xiangru RobertJin, Di
- Konferenz
- 1st Workshop on Taming Large Language Models : Controllability in the era of Interactive Assistants!, September 2023, Prag
- Verlagsangabe
- Association for Computational Linguistics : Prag
- Erscheinungsjahr
- 2023
- Sprache(n)
- Englisch
- URL
- 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-Schlagwort(e)
- Maschinelles LernenGenerierung <Sprache>GefühlPrompt Engineering
- Freie Schlagwort(e)
- Emotion-Conditioned Text Generation
- DDC-Klassifikation
- 004 Computer science
- RVK-Klassifikation
- ST 306
- Peer Reviewed
- ja
- Internationale Verbreitung
- ja
- Open-Access-Zeitschrift
- ja
- Dokumenttyp
- Konferenzveröffentlichung
- URI
- Datum der Freischaltung
- 07.03.2024
- Projekt(e)