ChatChecker: A Framework for Dialogue System Testing Through Non-cooperative User Simulation

Roman Mayr, Michel Schimpf, Thomas Bohné

Keywords: Large Language Models (LLMs), Dialogue System Testing, Multi-Turn Interaction, Breakdown Detection, User Simulation

TL;DR: We introduce ChatChecker, a framework that uses LLM-based user simulation and breakdown detection to automate scalable evaluation of multi-turn dialogue systems.

Abstract: While modern dialogue systems heavily rely on large language models (LLMs), their implementation often goes beyond pure LLM interaction. Developers integrate multiple LLMs, external tools, and databases. Therefore, assessment of the underlying LLM alone does not suffice and the dialogue systems must be tested and evaluated as a whole. However, this remains a major challenge. With most previous work focusing on turn-level analysis, less attention has been paid to integrated dialogue-level quality assurance. To address this, we present ChatChecker, a framework for automated evaluation and testing of complex dialogue systems. ChatChecker uses LLMs to simulate diverse multi-turn user interactions, identify dialogue breakdowns, and evaluate quality. Compared to previous approaches, our design reduces setup effort and is generalizable as it does not require reference dialogues and is decoupled from the implementation of the target dialogue system. We improve breakdown detection performance over a prior LLM-based approach by including an error taxonomy in the prompt. Additionally, we propose a novel non-cooperative user simulator based on challenging personas that uncovers weaknesses in target dialogue systems more effectively. Through this, ChatChecker contributes to thorough and scalable testing of multi-turn interactions.

Submission Number: 217