A Survey on LLM-based Conversational User Simulation

TL;DR

This survey reviews recent progress in LLM-based conversational user simulation, introducing a taxonomy, analyzing techniques, and highlighting open challenges to guide future research in the field.

Contribution

It provides a comprehensive taxonomy and systematic analysis of recent LLM-based conversational user simulation research, unifying existing work and identifying open challenges.

Findings

Introduces a novel taxonomy of user simulation based on granularity and objectives.

Analyzes core techniques and evaluation methods used in LLM-based user simulation.

Organizes existing research under a unified framework to facilitate future advancements.

Abstract

User simulation has long played a vital role in computer science due to its potential to support a wide range of applications. Language, as the primary medium of human communication, forms the foundation of social interaction and behavior. Consequently, simulating conversational behavior has become a key area of study. Recent advancements in large language models (LLMs) have significantly catalyzed progress in this domain by enabling high-fidelity generation of synthetic user conversation. In this paper, we survey recent advancements in LLM-based conversational user simulation. We introduce a novel taxonomy covering user granularity and simulation objectives. Additionally, we systematically analyze core techniques and evaluation methodologies. We aim to keep the research community informed of the latest advancements in conversational user simulation and to further facilitate future research by identifying open challenges and organizing existing work under a unified framework.