Large Language Model-Based Role-Play Simulation

Overview

This field studies how language models can simulate people and characters in interactive settings, from fictional worlds and customer conversations to clinical, educational, and social scenarios. Common approaches combine persona prompts with dialogue memory, psychological or knowledge-state models, multi-agent designs, and fine-tuning or reinforcement learning to shape behavior over multiple turns. Researchers evaluate realism, persona consistency, task outcomes, and safety using human judgments, dialogue benchmarks, and comparisons with real-world behavior. A central challenge is that fluent role-play can still fail to reflect a person's knowledge, motivations, or boundaries, while longer interactions can expose drift, bias, and unsafe responses.

Latest papers

CardsList

125 papers20 papers in the last four weeks, up 5% on the four weeks before. 0.2% of all new papers.

  1. CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamics

    Jan 15, 2026Viet Cuong Nguyen, Nhi Yen Nguyen, Kristin A. Candan +5Large Language Model-Based Role-Play SimulationSynthetic Data Generation for Language Models

  2. Simulating Student-Tutor Interactions with LLMs for Multilingual Math Feedback

    Jun 5, 2025Junior Cedric Tonga, KV Aditya Srivatsa, Kaushal Kumar Maurya +2Educational Feedback GenerationGenerative AI in Education