Mind the Goal: Data-Efficient Goal-Oriented Evaluation of Conversational Agents and Chatbots using Teacher Models
It addresses the problem of assessing goal fulfillment in conversational agents for developers and enterprises, offering actionable insights through a generic framework, though it is incremental as it builds on existing evaluation methods with a new focus.
The paper tackles the challenge of evaluating multi-turn chatbot interactions by focusing on whether user goals are fulfilled, proposing a goal-oriented evaluation framework with metrics like Goal Success Rate (GSR) and Root Cause of Failure (RCOF). In an enterprise application, this framework improved GSR from 63% to 79% over six months for a conversational agent system.
Evaluating the quality of multi-turn chatbot interactions remains challenging, as most existing methods assess interactions at the turn level without addressing whether a user's overarching goal was fulfilled. A ``goal'' here refers to an information need or task, such as asking for policy information or applying for leave. We propose a comprehensive framework for goal-oriented evaluation of multi-agent systems (MAS), introducing the \textbf{Goal Success Rate (GSR)} to measure the percentage of fulfilled goals, and a \textbf{Root Cause of Failure (RCOF)} taxonomy to identify reasons for failure in multi-agent chatbots. Our method segments conversations by user goals and evaluates success using all relevant turns. We present a model-based evaluation system combining teacher LLMs, where domain experts define goals, set quality standards serving as a guidance for the LLMs. The LLMs use ``thinking tokens'' to produce interpretable rationales, enabling \textit{explainable}, \textit{data-efficient} evaluations. In an enterprise setting, we apply our framework to evaluate AIDA, a zero-to-one employee conversational agent system built as a ground-up multi-agent conversational agent, and observe GSR improvement from 63\% to 79\% over six months since its inception. Our framework is generic and offers actionable insights through a detailed defect taxonomy based on analysis of failure points in multi-agent chatbots, diagnosing overall success, identifying key failure modes, and informing system improvements.