# Modeling the Sacred: Considerations when Using Religious Texts in Natural Language Processing

arXiv: https://arxiv.org/abs/2404.14740 · HTML: https://mlsanity.com/paper/2404.14740/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 73 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI](https://mlsanity.com/paper/2204.01075/) (2022)
- [Show Your Work: Improved Reporting of Experimental Results](https://mlsanity.com/paper/1909.03004/) (2019)
- [Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages](https://mlsanity.com/paper/2305.12182/) (2023)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [Evaluation Gaps in Machine Learning Practice](https://mlsanity.com/paper/2205.05256/) (2022)
- [Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP](https://mlsanity.com/paper/2109.06598/) (2021)
- [The Effect of Domain and Diacritics in Yor`ub'a-English Neural Machine Translation](https://mlsanity.com/paper/2103.08647/) (2021)
- [ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages](https://mlsanity.com/paper/2305.10510/) (2023)
- [Underspecification in Scene Description-to-Depiction Tasks](https://mlsanity.com/paper/2210.05815/) (2022)
- [Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold](https://mlsanity.com/paper/2206.09755/) (2022)
- [Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers](https://mlsanity.com/paper/2305.19474/) (2023)
- [Reusable Templates and Guides For Documenting Datasets and Models for Natural Language Processing and Generation: A Case Study of the HuggingFace and GEM Data and Model Cards](https://mlsanity.com/paper/2108.07374/) (2021)
- [Not always about you: Prioritizing community needs when developing endangered language technology](https://mlsanity.com/paper/2204.05541/) (2022)
- [A Human Rights-Based Approach to Responsible AI](https://mlsanity.com/paper/2210.02667/) (2022)
- [Geographic Citation Gaps in NLP Research](https://mlsanity.com/paper/2210.14424/) (2022)
- ["It's how you do things that matters": Attending to Process to Better Serve Indigenous Communities with Language Technologies](https://mlsanity.com/paper/2402.02639/) (2024)
- [Artificial intelligence for topic modelling in Hindu philosophy: mapping themes between the Upanishads and the Bhagavad Gita](https://mlsanity.com/paper/2205.11020/) (2022)
- [A Weakly Supervised Classifier and Dataset of White Supremacist Language](https://mlsanity.com/paper/2306.15732/) (2023)

## Built on by (most cited first, 1 of 1)

- [Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas](https://mlsanity.com/paper/2409.13979/) (2024)

## Abstract (arXiv)

This position paper concerns the use of religious texts in Natural Language Processing (NLP), which is of special interest to the Ethics of NLP. Religious texts are expressions of culturally important values, and machine learned models have a propensity to reproduce cultural values encoded in their training data. Furthermore, translations of religious texts are frequently used by NLP researchers when language data is scarce. This repurposes the translations from their original uses and motivations, which often involve attracting new followers. This paper argues that NLP's use of such texts raises considerations that go beyond model biases, including data provenance, cultural contexts, and their use in proselytism. We argue for more consideration of researcher positionality, and of the perspectives of marginalized linguistic and religious communities.