Loading
Life sciences · Preprint
arXiv · September 10, 2026
Early or partial results. Treat as a signal, not a conclusion.
This is a preprint describing an open-source conversational XAI system for interpreting energy consumption forecasting models, evaluated against a traditional dashboard by energy domain specialists. The work reports qualitative preference (unanimous preference for conversational interface) and a technical metric (94% intent-parsing accuracy), but lacks formal statistical analysis, sample size reporting, and peer review.
Comparative evaluation with domain expert assessment. Energy domain specialists; context: systems for interpreting energy consumption forecasting models used by facility managers and building operators. Intervention: Explainability Assistant: conversational XAI system leveraging Large Language Model function-calling capabilities for interpreting energy consumption ML models. Compared with: Traditional XAI dashboard.
System achieves 94% intent-parsing accuracy, compared to 76.8% for prior approach (TalkToModel) All experts unanimously preferred the conversational interface for practical use Evaluation suggests improved usability and consistent task accuracy
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
A proof-of-concept system evaluation with domain specialists showing improved usability over a comparator, but lacking rigorous human-factors methodology, sample size reporting, and peer review.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
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.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.