BrAIcht, a theatrical agent that speaks like Bertolt Brecht's characters

2025-04-29

AI Summary

This study addresses the challenge of controllable dialogue generation that faithfully reproduces Bertolt Brecht’s distinctive dramatic character language style. To this end, we introduce BrAIcht—the first dialogue agent explicitly designed for German theatrical style transfer. Methodologically, we construct a novel training corpus by integrating Brecht’s complete oeuvre of 29 plays with 907 stylistically aligned German dramas; fine-tune the German-adapted 7B-parameter LeoLM (a Llama-2 derivative) via QLoRA for efficient few-shot adaptation. Crucially, we propose a dual-metric evaluation framework combining BLEU and perplexity to jointly assess stylistic fidelity and linguistic fluency. Experimental results demonstrate that BrAIcht significantly outperforms all baselines on both metrics, confirming the feasibility of precise theatrical style transfer under low-resource conditions. This work establishes a scalable technical paradigm bridging digital humanities and interactive theatre.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

This project introduces BrAIcht, an AI conversational agent that creates dialogues in the distinctive style of the famous German playwright Bertolt Brecht. BrAIcht is fine-tuned using German LeoLM, a large language model with 7 billion parameters and a modified version of the base Llama2 suitable for German language tasks. For fine-tuning, 29 plays of Bertolt Brecht and 907 of other German plays that are stylistically similar to Bertolt Brecht are used to form a more di-erse dataset. Due to the limited memory capacity, a parameterefficient fine-tuning technique called QLoRA is implemented to train the large language model. The results, based on BLEU score and perplexity, show very promising performance of BrAIcht in generating dialogues in the style of Bertolt Brecht.

Problem

• Develop AI agent mimicking Brecht's dialogue style
• Fine-tune German LLM with limited memory capacity
• Evaluate performance using BLEU and perplexity metrics

Innovation

• Fine-tuned German LeoLM with 7B parameters
• Used QLoRA for efficient memory training
• Trained on 29 Brecht and 907 similar plays