Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Emotion-Conditioned Text Generation through Automatic Prompt Optimization

Publication

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

Author
Menchaca Resendiz, Yarik
Title of the compilation
Proceedings of the 1st Workshop on Taming Large Language Models : Controllability in the era of Interactive Assistants!
Editors
Hazarika, Devamanyu
Tang, Xiangru Robert
Jin, Di
Conference
1st Workshop on Taming Large Language Models : Controllability in the era of Interactive Assistants!, September 2023, Prag
Publisher Information
Association for Computational Linguistics : Prag
Year of publication
2023
Language
English
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 Keywords
Maschinelles Lernen
Generierung <Sprache>
Gefühl
Prompt 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
2024-03-07
Project(s)

Permalink: https://fis.uni-bamberg.de/handle/uniba/93873 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.