Gå direkt till huvudinnehåll
Researchdata.se

Multi-model Interreligious Roleplay Archive

MIRA
https://doi.org/10.5878/npy2-hk17
Datamängden består av 960 svar som samlades in år 2025 från olika stora språkmodeller (LLM). Språkmodellerna fick en religiös fråga att besvara i rollen som en av 12 teologiska personligheter (6 kristna och 6 muslimska). Fyra (4) olika modeller tillfrågades: Claude Sonnet 4, Gemini 2.5 Flash, GPT4o och GPT5. Två (2) olika kanaler användes för att ställa frågor och samla in svar: API och webbgränssnitt. Tio (10) svar samlades in för varje kombination av de ovanstående parametrarna. Data finns tillgängliga som en xlsx-fil. Frågorna och rollfigurerna finns tillgängliga som en PDF-fil.
Ladda ner data och dokumentation (4 filer / 2.95 MiB)

Datafiler

  • outputs.csv
    2.18 MiB
  • outputs.xlsx
    699.36 KiB
  • prompt.pdf
    87.73 KiB

Dokumentationsfiler

  • README.txt
    2.4 KiB

Citering och åtkomst

Tillgänglighetsnivå:

Skapare/primärforskare:

Forskningshuvudman:

Diarienummer hos huvudman:

  • LNU-2024/990

Data innehåller personuppgifter:

Nej

Citering:

Licens:

Språk:

Metod och utfall

Analysenhet:

Population:

Outputs from large language models

Tidsdimension:

Urvalsmetod:

Beskrivning av urval:

Four prominent and current LLMs were employed: Open AI's GPT-4o and GPT-5, Anthropic’s Claude 4.1 and Google’s Gemini 2.5. Twelve personas were created, six within the Christian tradition and six within Islam; the personas from each religion are not meant to correspond to one another, but offer a comparable range of internal diversity for assessing large language models' performances (based on the expertise of the religious scholars involved). Two channels for data collection were selected for comparison: the web user interfaces (e.g. ChatGPT) and APIs. Finally, under the conditions above, an output for the given prompt was collected 10 times.

Tidsperiod(er) som undersökts:

Variabler:

6

Antal individer/objekt:

960

Dataformat/datastruktur:

Datainsamling Automatiserad dataextrahering: webbskrapning

Insamlingsmetod:

Automatiserad dataextrahering: webbskrapning

Beskrivning av insamlingsmetod:

Web-scraping conducted within the default web environment of each model using anonymous browser windows to ensure that responses were not influenced by any prior conversational context. The free-of-charge versions of the chatbots were used in the experiment. When the limits of the conversation were reached, the researcher waited for a new free time slot to continue the prompting. Furthermore, the temperature was not increased and remained at its default values, and the thinking mode feature was not activated to maintain a standard baseline response. The models were prompted to stay in their answers as close to the 500 tokens as possible without interrupting the thought chain. Responses to prompts were copied and saved in an Excel sheet that was later shared with all other members of the research team.

Tidsperiod(er) för datainsamling:

2025-08-15 - 2025-08-22

Datainsamling Automatiserad dataextrahering: webbskrapning

Insamlingsmetod:

Automatiserad dataextrahering: webbskrapning

Beskrivning av insamlingsmetod:

API extraction was conducted without a token-length restriction, allowing the models to determine response length. Sub-datasets from individual models where responses were cut off have been saved, but do not appear in the final dataset. A middle temperature setting was chosen across all models and all runs, and leave temperature as a variable for future research.

Tidsperiod(er) för datainsamling:

2025-09-01 - 2025-09-01

Administrativ information

Ansvarig institution/enhet:

Institutionen för kulturvetenskaper

Finansiering

Finansiär:

Referensnummer:

P24-0313

URI hos finansiär:

https://www.rj.se/en/grants/2024/artificial-ulama--patterns-and-biases-in-non-human-islam/Öppnas i en ny tabb

Projektnamn på ansökan:

Artificiella ‘ulama – Mönster och partiskhet i icke-mänsklig islam

Finansiär:

  • Ministry of Education, Youth and Sports of the Czech Republic (co-financed by the European Union)

Referensnummer:

CZ.02.01.01/00/23_025/0008691

Information om finansiering:

This work was supported by the project “ Human-centred AI for a Sustainable and Adaptive Society” (reg. no.: CZ.02.01.01/00/23_025/0008691), co-funded by the European Union.

Ämnesområde och nyckelord

CESSDA Topic Classification:

Standard för svensk indelning av forskningsämnen 2025:

Nyckelord:

Metadata

Version 1
doris
Linnéuniversitetet
Publicerad: