# PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations

arXiv: https://arxiv.org/abs/2603.06485 · HTML: https://mlsanity.com/paper/2603.06485/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Human-Centered Explainable AI (XAI): From Algorithms to User Experiences](https://mlsanity.com/paper/2110.10790/) (2021)
- [What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research](https://mlsanity.com/paper/2102.07817/) (2021)
- [Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations](https://mlsanity.com/paper/2210.11584/) (2022)
- [Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs](https://mlsanity.com/paper/2101.09824/) (2021)
- [LLMs for Explainable AI: A Comprehensive Survey](https://mlsanity.com/paper/2504.00125/) (2025)
- [Tell Me a Story! Narrative-Driven XAI with Large Language Models](https://mlsanity.com/paper/2309.17057/) (2023)
- [LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations](https://mlsanity.com/paper/2509.09396/) (2025)
- [User Characteristics in Explainable AI: The Rabbit Hole of Personalization?](https://mlsanity.com/paper/2403.00137/) (2024)
- [GraphXAIN: Narratives to Explain Graph Neural Networks](https://mlsanity.com/paper/2411.02540/) (2024)
- [How good is my story? Towards quantitative metrics for evaluating LLM-generated XAI narratives](https://mlsanity.com/paper/2412.10220/) (2024)
- [Towards Balancing Preference and Performance through Adaptive Personalized Explainability](https://mlsanity.com/paper/2504.13856/) (2025)
- [When Large Language Models Know the Table: A Framework for Assessing Data Contamination in Tabular Datasets](https://mlsanity.com/paper/2510.20351/) (2025)
- [Comparative Explanations: Explanation Guided Decision Making for Human-in-the-Loop Preference Selection](https://mlsanity.com/paper/2504.03744/) (2025)
- [Enhancing XAI Narratives through Multi-Narrative Refinement and Knowledge Distillation](https://mlsanity.com/paper/2510.03134/) (2025)

## Built on by (most cited first, 1 of 1)

- [Explaining AI Agents Through Execution Traces](https://mlsanity.com/paper/2609.06063/) (2026)

## Abstract (arXiv)

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.