mlsanityData to 7 Oct 2026

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

arXiv 2404.14740 ↗First posted 23 Apr 2024cs.CLcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 73 references that are in the map. First posted on arXiv 23 Apr 2024.

Builds on

23 of 73 references.

References · 23

  1. 2018Datasheets for Datasetscited by 1,371
  2. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  3. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  4. 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
  5. 2023MADLAD-400: A Multilingual And Document-Level Large Audited Datasetcited by 180
  6. 2022Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AIcited by 169
  7. 2019Show Your Work: Improved Reporting of Experimental Resultscited by 164
  8. 2023Glot500: Scaling Multilingual Corpora and Language Models to 500 Languagescited by 116
  9. 2023NLPositionality: Characterizing Design Biases of Datasets and Modelscited by 91
  10. 2022Evaluation Gaps in Machine Learning Practicecited by 48
  11. 2021Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLPcited by 47
  12. 2021The Effect of Domain and Diacritics in Yor`ub'a-English Neural Machine Translationcited by 38
11 more
  1. 2023ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languagescited by 33
  2. 2022Underspecification in Scene Description-to-Depiction Taskscited by 30
  3. 2022Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifoldcited by 29
  4. 2023Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakerscited by 26
  5. 2021Reusable 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 Cardscited by 24
  6. 2022Not always about you: Prioritizing community needs when developing endangered language technologycited by 21
  7. 2022A Human Rights-Based Approach to Responsible AIcited by 20
  8. 2022Geographic Citation Gaps in NLP Researchcited by 19
  9. 2024"It's how you do things that matters": Attending to Process to Better Serve Indigenous Communities with Language Technologiescited by 12
  10. 2022Artificial intelligence for topic modelling in Hindu philosophy: mapping themes between the Upanishads and the Bhagavad Gitacited by 6
  11. 2023A Weakly Supervised Classifier and Dataset of White Supremacist Languagecited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmascited by 6