Breaking the Assistant Mold: Modeling Behavioral Variation in LLM Based Procedural Character Generation

TL;DR

This paper introduces PersonaWeaver, a framework for creating diverse, realistic characters in procedural generation by disentangling roles from behavioral traits, addressing biases in existing methods.

Contribution

It presents a novel disentanglement approach that enhances behavioral diversity and reduces alignment-induced biases in large language model-based character generation.

Findings

Characters exhibit more diverse moral stances and interaction styles.

The framework increases stylistic variation like tone and punctuation.

Code is available at the provided GitHub repository.

Abstract

Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underexplored. We identify two alignment-induced biases in existing methods: a positive moral bias, where characters uniformly adopt agreeable stances (e.g. always saying lying is bad), and a helpful assistant bias, where characters invariably answer questions directly (e.g. never refusing or deflecting). While such tendencies suit instruction-following systems, they suppress dramatic tension and yield predictable characters, stemming from maximum likelihood training and assistant fine-tuning. To address this, we introduce PersonaWeaver, a framework that disentangles world-building (roles, demographics) from behavioral-building (moral stances, interactional styles), yielding characters with more diverse reactions and moral stances, as well as second-order diversity in stylistic markers like length, tone, and punctuation. Code: https://github.com/mqraitem/Persona-Weaver