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

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

13 Dec 2024arXiv:2412.10220archive 2025-07-28

Timour Ichmoukhamedov, James Hinns, David Martens

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.

PaperPDFCode

Code

admantwerp/shapnarrative-metrics officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

tabular-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SHAP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections