# How good is my story? Towards quantitative metrics for evaluating LLM-generated XAI narratives

arXiv: https://arxiv.org/abs/2412.10220 · HTML: https://mlsanity.com/paper/2412.10220/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2024.

## Built on by (most cited first, 7 of 7)

- [LLMs for Explainable AI: A Comprehensive Survey](https://mlsanity.com/paper/2504.00125/) (2025)
- [An Agentic Approach to Generating XAI-Narratives](https://mlsanity.com/paper/2603.20003/) (2026)
- [Enhancing XAI Narratives through Multi-Narrative Refinement and Knowledge Distillation](https://mlsanity.com/paper/2510.03134/) (2025)
- [PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations](https://mlsanity.com/paper/2603.06485/) (2026)
- [A Two-Stage LLM Framework for Accessible and Verified XAI Explanations](https://mlsanity.com/paper/2604.12543/) (2026)
- [Measuring Information Distortion in Hierarchical Ultra long Novel Reconstruction:The Optimal Expansion Ratio](https://mlsanity.com/paper/2505.12572/) (2025)
- [On the Importance and Evaluation of Narrativity in Natural Language AI Explanations](https://mlsanity.com/paper/2604.18311/) (2026)

## Abstract (arXiv)

A rapidly developing application of LLMs in XAI is to convert quantitative explanations such as SHAP into user-friendly narratives to explain the decisions made by smaller prediction models. Evaluating the narratives without relying on human preference studies or surveys is becoming increasingly important in this field. In this work we propose a framework and explore several automated metrics to evaluate LLM-generated narratives for explanations of tabular classification tasks. We apply our approach to compare several state-of-the-art LLMs across different datasets and prompt types. As a demonstration of their utility, these metrics allow us to identify new challenges related to LLM hallucinations for XAI narratives.