Saved in:
Bibliographic Details
Main Authors: Lukassen, Fabian, Herrmann, Jan, Weisser, Christoph, Silbersdorff, Alexander, Saefken, Benjamin, Kneib, Thomas
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.26770
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914604380061696
author Lukassen, Fabian
Herrmann, Jan
Weisser, Christoph
Silbersdorff, Alexander
Saefken, Benjamin
Kneib, Thomas
author_facet Lukassen, Fabian
Herrmann, Jan
Weisser, Christoph
Silbersdorff, Alexander
Saefken, Benjamin
Kneib, Thomas
contents Prior work shows that Large Language Models (LLMs) can transform Explainable AI (XAI) outputs into Natural Language Explanations (NLEs) that score highly on quality metrics such as plausibility, coherence, and comprehensibility. But does explanation quality translate to practical usefulness? We investigate this question in a time-series energy forecasting domain through five controlled experiments (2,730 judgments across 60 test instances), each operationalising a distinct facet of usefulness studied in the XAI literature. Holding NLE quality constant at the high levels established by a prior factorial study, we find that NLEs do not improve task accuracy on any of the five tasks, while inflating self-reported confidence. A placebic control shows that this confidence boost is driven by text presence rather than content. In an out-of-distribution detection task, NLEs reduce the LLM judge's ability to flag unreliable predictions, providing false reassurance that masks model failure. We characterise these findings as the Quality-Usefulness Gap and argue that evaluation of the XAI-to-NLE pipeline must extend beyond text-quality metrics to downstream task performance.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26770
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aids
Lukassen, Fabian
Herrmann, Jan
Weisser, Christoph
Silbersdorff, Alexander
Saefken, Benjamin
Kneib, Thomas
Computation and Language
Prior work shows that Large Language Models (LLMs) can transform Explainable AI (XAI) outputs into Natural Language Explanations (NLEs) that score highly on quality metrics such as plausibility, coherence, and comprehensibility. But does explanation quality translate to practical usefulness? We investigate this question in a time-series energy forecasting domain through five controlled experiments (2,730 judgments across 60 test instances), each operationalising a distinct facet of usefulness studied in the XAI literature. Holding NLE quality constant at the high levels established by a prior factorial study, we find that NLEs do not improve task accuracy on any of the five tasks, while inflating self-reported confidence. A placebic control shows that this confidence boost is driven by text presence rather than content. In an out-of-distribution detection task, NLEs reduce the LLM judge's ability to flag unreliable predictions, providing false reassurance that masks model failure. We characterise these findings as the Quality-Usefulness Gap and argue that evaluation of the XAI-to-NLE pipeline must extend beyond text-quality metrics to downstream task performance.
title Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aids
topic Computation and Language
url https://arxiv.org/abs/2605.26770