README
======

Dataset title:
Multi-model Interreligious Roleplay Archive (MIRA)

Recommended Citation: 
Kamal, A.M., Lipkova, H., Radde-Antweiler, K., & Svensson, J. (2026). Multi-model Interreligious Roleplay Archive (MIRA) (Version 1) [Data set]. Linnaeus University. Available at: https://doi.org/10.5878/npy2-hk17

Creators:
Ahmad M. Kamal, Helena Lipkova, Kerstin Radde-Antweiler, & Jonas Svensson

Responsible organization:
Linnaeus University

See the Researchdata.se catalogue entry for this dataset for complete metadata, including the dataset description, recommended citation, contact information, and information about how to obtain the dataset. 

Description: The dataset consists of 960 outputs collected in 2025 from various large language models (LLMs). The LLMs were given a religious question to answer as one of 12 theological personas (6 Christian and 6 Muslim). Four (4) different models were queried: Claude Sonnet 4, Gemini 2.5 Flash, GPT4o,  and GPT5. Two (2) different channels were used for prompting and collecting outputs: API and web user-interface. Ten (10) outputs were collected for each combination of the preceding parameters. The data is available as a xlsx file. The prompt and personas are available as a PDF.

License: Creative Commons Attribution 4.0 International (CC-BY 4.0)

Access restrictions: N/A

Essential information for dataset reuse.
----------------------------------------

The data consists of 960 outputs collected in 2025 from several large language models (LLMs). The LLMs were given a religious question to answer as one of 12 theological personas (6 Christian and 6 Muslim). Four (4) different models were queried: Claude Sonnet 4, Gemini 2.5 Flash, GPT4o,  and GPT5, both through API and web user-interface. 10 responses were collected for each parameter. The data is available as a xlsx file. The prompt and personas are available as a PDF. The sampling procedure was non-probablistic (quota), collecting 10 outputs under each specific combination of model, persona, and channel.


Datafile descriptions
----------------------

prompt.pdf - The query and personas given to the LLMs for the outputs generated.

outputs.xlsx - Table of outputs from LLMs according to 4 parameters: models (4), channels (2), personas (12), and runs (10).

outputs.csv – Table of outputs from LLMs according to 4 parameters: models (4), channels (2), personas (12), and runs (10).
