A Survey on Multi-Turn Interaction Capabilities of Large Language Models

TL;DR

This survey reviews the multi-turn interaction capabilities of large language models, highlighting their importance for various applications, evaluation methods, core model features, and future research directions.

Contribution

It provides a comprehensive overview of the current state, evaluation practices, and algorithms for multi-turn interactions in large language models, and discusses future research directions.

Findings

Large language models have significantly advanced multi-turn interaction capabilities.

Evaluation methods for multi-turn interactions are diverse and evolving.

Future research should focus on improving coherence and context retention.

Abstract

Multi-turn interaction in the dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling it to generate coherent and contextually relevant responses. Recent advancements in large language models (LLMs) have significantly expanded the scope of multi-turn interaction, moving beyond chatbots to enable more dynamic agentic interactions with users or environments. In this paper, we provide a focused review of the multi-turn capabilities of LLMs, which are critical for a wide range of downstream applications, including conversational search and recommendation, consultation services, and interactive tutoring. This survey explores four key aspects: (1) the core model capabilities that contribute to effective multi-turn interaction, (2) how multi-turn interaction is evaluated in current practice, (3) the general algorithms used to enhance multi-turn interaction, and (4) potential future directions for research in this field.