Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness

Ulysse Maes; Lien Michiels; Annelien Smets

Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness

Ulysse Maes, Lien Michiels, Annelien Smets

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

1 Downloads (Pure)

Original language	English
Title of host publication	Joint Proceedings of the ACM IUI 2025 Workshops co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025)
Publisher	CEUR Workshop Proceedings
Number of pages	17
Publication status	Published - 2025

Publication series

Name	CEUR Workshop Proceedings
ISSN (Print)	1613-0073

Access to Document

11Final published version, 847 KBLicence: CC BY

https://axai.trx.li/papers/11.pdfLicence: CC BY

Handle.net

Persistent link

FWOTM1251: Nudging towards viewpoint diversity? Evaluating the impact of LLM-enabled explanations on diversity consumption in news recommender
Maes, U. (Mandate), Smets, A. (Administrative Promotor) & Raats, T. (CoI (Co-Promotor))
1/11/24 → 31/10/28
Project: Fundamental
FWOSBO50: SBO Project with primary societal finality: Serendipity Engine: towards surprising and interesting urban experiences
Ballon, P. (Administrative Promotor) & Smets, A. (CoI (Co-Promotor))
1/10/22 → 30/09/26
Project: Applied

Cite this

Maes, U., Michiels, L., & Smets, A. (2025). Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness. In Joint Proceedings of the ACM IUI 2025 Workshops co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025) (CEUR Workshop Proceedings). CEUR Workshop Proceedings. https://axai.trx.li/papers/11.pdf

Maes, Ulysse ; Michiels, Lien ; Smets, Annelien. / Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness. Joint Proceedings of the ACM IUI 2025 Workshops co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025). CEUR Workshop Proceedings, 2025. (CEUR Workshop Proceedings).

@inproceedings{1ab16772d94f4d858f96ad6dd2011db8,

title = "Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness",

author = "Ulysse Maes and Lien Michiels and Annelien Smets",

year = "2025",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR Workshop Proceedings",

booktitle = "Joint Proceedings of the ACM IUI 2025 Workshops co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025)",

}

Maes, U , Michiels, L & Smets, A 2025, Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness. in Joint Proceedings of the ACM IUI 2025 Workshops co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025). CEUR Workshop Proceedings, CEUR Workshop Proceedings. <https://axai.trx.li/papers/11.pdf>

Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness. / Maes, Ulysse ; Michiels, Lien ; Smets, Annelien.
Joint Proceedings of the ACM IUI 2025 Workshops co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025). CEUR Workshop Proceedings, 2025. (CEUR Workshop Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

TY - GEN

T1 - Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness

AU - Maes, Ulysse

AU - Michiels, Lien

AU - Smets, Annelien

PY - 2025

Y1 - 2025

M3 - Conference paper

T3 - CEUR Workshop Proceedings

BT - Joint Proceedings of the ACM IUI 2025 Workshops co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025)

PB - CEUR Workshop Proceedings

ER -

Maes U , Michiels L , Smets A. Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness. In Joint Proceedings of the ACM IUI 2025 Workshops co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025). CEUR Workshop Proceedings. 2025. (CEUR Workshop Proceedings).

Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness

Publication series

Access to Document

Handle.net

Projects

FWOTM1251: Nudging towards viewpoint diversity? Evaluating the impact of LLM-enabled explanations on diversity consumption in news recommender

FWOSBO50: SBO Project with primary societal finality: Serendipity Engine: towards surprising and interesting urban experiences

Cite this