Who Gets the Better Story? An Exploration of Fairness in Explainable AI Narratives for Credit Scoring

Wannes Van den Bulck, Sofie Goethals, David Martens
Proceedings of Fifth European Conference on Algorithmic Fairness, PMLR 350:107-112, 2026.

Abstract

Post-hoc explanation methods like SHAP can technically justify credit decisions but are too technical for lay people to interpret, motivating AI-generated explanatory narratives (XAIN) that use large language models (LLMs) to translate SHAP artefacts into natural language. While prior work has evaluated narrative faithfulness at the aggregate level, no study has examined whether quality differs systematically across demographic groups. We generate 204 SHAP-based narratives across six LLM providers for adversely classified instances from the German Credit dataset and break down faithfulness and feature coverage by applicant sex and age. We find substantial provider-level heterogeneity in narrative content, age- and sex-based disparities in which features are mentioned, and faithfulness differences across social groups. These exploratory findings underscore that XAIN cannot yet be deployed without structured fairness auditing and that further research is warranted.

Cite this Paper

BibTeX
@InProceedings{pmlr-v350-bulck26a, title = {Who Gets the Better Story? An Exploration of Fairness in Explainable AI Narratives for Credit Scoring}, author = {Van den Bulck, Wannes and Goethals, Sofie and Martens, David}, booktitle = {Proceedings of Fifth European Conference on Algorithmic Fairness}, pages = {107--112}, year = {2026}, editor = {De Bie, Tijl and Defrance, MaryBeth and Calders, Toon and Nguyen, Dennis}, volume = {350}, series = {Proceedings of Machine Learning Research}, month = {02--04 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v350/main/assets/bulck26a/bulck26a.pdf}, url = {https://proceedings.mlr.press/v350/bulck26a.html}, abstract = {Post-hoc explanation methods like SHAP can technically justify credit decisions but are too technical for lay people to interpret, motivating AI-generated explanatory narratives (XAIN) that use large language models (LLMs) to translate SHAP artefacts into natural language. While prior work has evaluated narrative faithfulness at the aggregate level, no study has examined whether quality differs systematically across demographic groups. We generate 204 SHAP-based narratives across six LLM providers for adversely classified instances from the German Credit dataset and break down faithfulness and feature coverage by applicant sex and age. We find substantial provider-level heterogeneity in narrative content, age- and sex-based disparities in which features are mentioned, and faithfulness differences across social groups. These exploratory findings underscore that XAIN cannot yet be deployed without structured fairness auditing and that further research is warranted.} }
Endnote
%0 Conference Paper %T Who Gets the Better Story? An Exploration of Fairness in Explainable AI Narratives for Credit Scoring %A Wannes Van den Bulck %A Sofie Goethals %A David Martens %B Proceedings of Fifth European Conference on Algorithmic Fairness %C Proceedings of Machine Learning Research %D 2026 %E Tijl De Bie %E MaryBeth Defrance %E Toon Calders %E Dennis Nguyen %F pmlr-v350-bulck26a %I PMLR %P 107--112 %U https://proceedings.mlr.press/v350/bulck26a.html %V 350 %X Post-hoc explanation methods like SHAP can technically justify credit decisions but are too technical for lay people to interpret, motivating AI-generated explanatory narratives (XAIN) that use large language models (LLMs) to translate SHAP artefacts into natural language. While prior work has evaluated narrative faithfulness at the aggregate level, no study has examined whether quality differs systematically across demographic groups. We generate 204 SHAP-based narratives across six LLM providers for adversely classified instances from the German Credit dataset and break down faithfulness and feature coverage by applicant sex and age. We find substantial provider-level heterogeneity in narrative content, age- and sex-based disparities in which features are mentioned, and faithfulness differences across social groups. These exploratory findings underscore that XAIN cannot yet be deployed without structured fairness auditing and that further research is warranted.
APA
Van den Bulck, W., Goethals, S. & Martens, D.. (2026). Who Gets the Better Story? An Exploration of Fairness in Explainable AI Narratives for Credit Scoring. Proceedings of Fifth European Conference on Algorithmic Fairness, in Proceedings of Machine Learning Research 350:107-112 Available from https://proceedings.mlr.press/v350/bulck26a.html.

Related Material