The Oscars of AI Theater: A Survey on Role-Playing with Language Models

TL;DR

This survey reviews the evolution, methodologies, and challenges of role-playing with language models, highlighting advancements from simple personas to complex character simulations and proposing future research directions.

Contribution

It provides a comprehensive taxonomy of role-playing system components, summarizes current methodologies, and identifies key challenges and future research avenues in the field.

Findings

Role-playing with LLMs has evolved from simple persona consistency to complex character simulations.

Current challenges include managing dynamic profiles and ensuring high persona consistency.

The survey offers a structured overview and future research directions for improving role-playing applications.

Abstract

This survey explores the burgeoning field of role-playing with language models, focusing on their development from early persona-based models to advanced character-driven simulations facilitated by Large Language Models (LLMs). Initially confined to simple persona consistency due to limited model capabilities, role-playing tasks have now expanded to embrace complex character portrayals involving character consistency, behavioral alignment, and overall attractiveness. We provide a comprehensive taxonomy of the critical components in designing these systems, including data, models and alignment, agent architecture and evaluation. This survey not only outlines the current methodologies and challenges, such as managing dynamic personal profiles and achieving high-level persona consistency but also suggests avenues for future research in improving the depth and realism of role-playing applications. The goal is to guide future research by offering a structured overview of current methodologies and identifying potential areas for improvement. Related resources and papers are available at https://github.com/nuochenpku/Awesome-Role-Play-Papers.