Explainability assistant improves energy model understanding with conversation
Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models
Artificial IntelligenceMachine Learning
Summary
Energy forecasting models can be hard to understand for people who manage buildings. The authors created a conversational assistant that helps users ask questions in natural language and get clear explanations about these models. Unlike older systems with limited ways to ask questions, this assistant uses advanced language tools to better understand user intent and works well without extra training. Experts testing the system preferred it over traditional dashboards for ease of use and accuracy.
What this means in practice
- •For facility managers: Use conversational queries to understand complex energy models without technical expertise, improving building energy management decisions.
- •For data analytics teams: Integrate conversational explainability to enable non-technical stakeholders to interact naturally with machine learning model interpretations.
Authors
Rodion Krjutškov, Eduard Barbu, Nikos Sakkas, Sofia Yfanti
Abstract
Energy consumption forecasting relies on increasingly complex machine learning (ML) models, such as Genetic Programming-based symbolic regressors, whose predictions can be difficult for facility managers and building operators to interpret. Explainable Artificial Intelligence (XAI) techniques address this opacity, but traditional XAI dashboards require substantial technical expertise and provide limited flexibility for dynamic, context-aware inquiry. Conversational XAI systems offer a promising alternative; however, previous approaches, such as TalkToModel, were constrained by rigid custom grammars and achieved only 76.8% intent-parsing accuracy. This paper introduces the Explainability Assistant, an open-source conversational XAI system that leverages the function-calling capabilities of modern Large Language Models (LLMs) to overcome these limitations. The system achieves 94% intent-parsing accuracy, supports flexible natural language interaction, and adapts to different ML problem types without task-specific fine-tuning. We present the system's architecture and report results from a comparative evaluation conducted with energy domain specialists, contrasting the Explainability Assistant with a traditional XAI dashboard. The evaluation suggests improved usability and consistent task accuracy, with all experts unanimously preferring the conversational interface for practical use.