PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations

2026-03-06

AI Summary

This work addresses the limitations of existing explainable AI (XAI) methods, which often adopt a one-size-fits-all paradigm that overlooks variations in users’ expertise, goals, and cognitive needs, and suffer from distortion and hallucination in natural language explanations generated by large language models. To overcome these issues, the authors propose a human-in-the-loop adaptive explanation framework that formulates personalization as a closed-loop validation and refinement process. The framework integrates a low-dimensional preference model, a structured XAI artifact–guided generator, a multi-dimensional verification module assessing numerical faithfulness and informational completeness, and a human feedback–driven preference update mechanism. Experiments in healthcare and finance demonstrate significant improvements in explanation completeness, stylistic alignment, and generation stability, while user studies confirm the accuracy and reliability of its style control.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm that neglects user differences in expertise, goals, and cognitive needs. Although Large Language Models can translate technical explanations into natural language, they introduce challenges related to faithfulness and hallucinations. To address these challenges, we present PONTE (Personalized Orchestration for Natural language Trustworthy Explanations), a human-in-the-loop framework for adaptive and reliable XAI narratives. PONTE models personalization as a closed-loop validation and adaptation process rather than prompt engineering. It combines: (i) a low-dimensional preference model capturing stylistic requirements; (ii) a preference-conditioned generator grounded in structured XAI artifacts; and (iii) verification modules enforcing numerical faithfulness, informational completeness, and stylistic alignment, optionally supported by retrieval-grounded argumentation. User feedback iteratively updates the preference state, enabling quick personalization. Automatic and human evaluations across healthcare and finance domains show that the verification-refinement loop substantially improves completeness and stylistic alignment over validation-free generation. Human studies further confirm strong agreement between intended preference vectors and perceived style, robustness to generation stochasticity, and consistently positive quality assessments.

Problem

• Explainable Artificial Intelligence
• personalization
• faithfulness
• hallucinations
• natural language explanations

Innovation

• Personalized XAI
• Closed-loop Validation
• Preference Modeling
• Faithful Natural Language Generation
• Human-in-the-loop Explanation