Work

Preserving Identity, Losing Practice: Religious Schema Transfer in Culturally Grounded Multi-Turn LLM Advice

Year: 2026

Type: conference-paper

Abstract: Large language models (LLMs) increasingly provide practical advice in contexts where users' religious identities are relevant.Existing evaluations of religion in language models have primarily examined stereotypes, representational bias, omission, emotional attribution, or differential treatment across religious groups.We study a different failure mode: whether an LLM preserves the correspondence between a user's religious identity

DOI: 10.18653/2026.oracle-main.25

Authors: Muhammad Junaid Iqbal, Fabio Massimo Zanzotto, Usman Nawaz, Tahir Alyas

Institutions: University of Rome Tor Vergata, University of Palermo, Lahore Garrison University

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

OpenAlex ID: W7224460306

FWCI:

Cites: 3

Cited by:

Related to: 10