Beyond single-model XAI: aggregating multi-model explanations for enhanced trustworthiness

2025-10-13

AI Summary

Current XAI methods suffer from insufficient explanation robustness and low decision transparency in high-stakes scenarios, undermining AI system trustworthiness. To address this, we propose a Multi-Model Feature Importance Aggregation (MMFIA) framework that fuses local feature importance explanations from heterogeneous models—including k-nearest neighbors, random forests, and neural networks—to mitigate single-model bias and enhance explanation stability and reproducibility. MMFIA imposes no assumptions on model homogeneity or differentiability, supports black-box system integration, and incorporates a weighted consistency mechanism to suppress noisy explanations. Experiments across multiple high-risk benchmark datasets demonstrate that MMFIA significantly improves explanation robustness (average gain of 23.6%) and user trust, while preserving predictive performance. This work establishes a scalable, model-agnostic paradigm for explanation aggregation, advancing the development of trustworthy AI systems.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The use of Artificial Intelligence (AI) models in real-world and high-risk applications has intensified the discussion about their trustworthiness and ethical usage, from both a technical and a legislative perspective. The field of eXplainable Artificial Intelligence (XAI) addresses this challenge by proposing explanations that bring to light the decision-making processes of complex black-box models. Despite being an essential property, the robustness of explanations is often an overlooked aspect during development: only robust explanation methods can increase the trust in the system as a whole. This paper investigates the role of robustness through the usage of a feature importance aggregation derived from multiple models ($k$-nearest neighbours, random forest and neural networks). Preliminary results showcase the potential in increasing the trustworthiness of the application, while leveraging multiple model's predictive power.

Problem

• Aggregating multi-model explanations to enhance AI trustworthiness
• Addressing robustness limitations in single-model XAI methods
• Leveraging multiple models' predictive power for reliable explanations

Innovation

• Aggregating feature importance from multiple models
• Using k-nearest neighbours, random forest, neural networks
• Enhancing explanation robustness for trustworthy AI systems