# Emotion-Conditioned Text Generation through Automatic Prompt Optimization

arXiv: https://arxiv.org/abs/2308.04857 · HTML: https://mlsanity.com/paper/2308.04857/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [UL2: Unifying Language Learning Paradigms](https://mlsanity.com/paper/2205.05131/) (2022)
- [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://mlsanity.com/paper/2109.04332/) (2021)
- [Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification](https://mlsanity.com/paper/2108.02035/) (2021)
- [Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory](https://mlsanity.com/paper/1704.01074/) (2017)
- [OpenPrompt: An Open-source Framework for Prompt-learning](https://mlsanity.com/paper/2111.01998/) (2021)
- [Planning with Learned Entity Prompts for Abstractive Summarization](https://mlsanity.com/paper/2104.07606/) (2021)
- [A Plug-and-Play Method for Controlled Text Generation](https://mlsanity.com/paper/2109.09707/) (2021)
- [Affect-LM: A Neural Language Model for Customizable Affective Text Generation](https://mlsanity.com/paper/1704.06851/) (2017)
- [Dimensional Modeling of Emotions in Text with Appraisal Theories: Corpus Creation, Annotation Reliability, and Prediction](https://mlsanity.com/paper/2206.05238/) (2022)
- [Towards Unified Prompt Tuning for Few-shot Text Classification](https://mlsanity.com/paper/2205.05313/) (2022)
- [Contrastive Learning for Prompt-Based Few-Shot Language Learners](https://mlsanity.com/paper/2205.01308/) (2022)
- [Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora](https://mlsanity.com/paper/2209.06701/) (2022)
- [Affective Natural Language Generation of Event Descriptions through Fine-grained Appraisal Conditions](https://mlsanity.com/paper/2307.14004/) (2023)

## Built on by (most cited first, 6 of 6)

- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [MOPO: Multi-Objective Prompt Optimization for Affective Text Generation](https://mlsanity.com/paper/2412.12948/) (2024)
- [Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations](https://mlsanity.com/paper/2509.13680/) (2025)
- [ELSA: A Style Aligned Dataset for Emotionally Intelligent Language Generation](https://mlsanity.com/paper/2504.08281/) (2025)
- [Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts](https://mlsanity.com/paper/2602.06692/) (2026)
- [iPOE: Interpretable Prompt Optimization via Explanations](https://mlsanity.com/paper/2605.18113/) (2026)

## Abstract (arXiv)

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.