Elamur Research⌕
☰
home / papers / 2024 / Having Beer after Prayer? Measuring Cultural Bias in Large Language Models

Having Beer after Prayer? Measuring Cultural Bias in Large Language Models

Paper · 2024 · Tarek Naous, Michael J Ryan, Alan Ritter et al.

Summary

Language models now serve users worldwide, but it is seldom checked whether they adapt to the cultural setting a non-English prompt implies. This paper studies Arabic and asks whether models lean toward Western entities even when the context clearly signals Arab culture. One example is proposing alcoholic drinks right after a mention of evening prayer. The authors build CAMeL, a benchmark with two parts:

  • Entities: 20,368 Arab and Western entities across eight types, collected from Wikidata and by pattern matching over Arabic CommonCrawl.
  • Prompts: 628 prompts taken from real Twitter/X posts, with the original entity replaced by a mask.

They use it to probe 16 LMs trained with Arabic data on four tasks: generating stories, recognizing named entities, classifying sentiment, and filling in masked text. Models produce stereotyped stories, perform unequally across cultures, and favour Western entities even in contexts tailored to Arab culture. Training n-gram LMs on six Arabic pre-training corpora points to data as one cause: Wikipedia leans Western, while local news and Twitter/X are more culturally grounded. The takeaway is that fluency in a language does not guarantee cultural fit.

Key points

  • CAMeL has 628 masked prompts and 20,368 entities of eight types: person names, food dishes, beverages, clothing, cities, literary authors, places of worship and sports clubs. "Western" here means Western Europe and North America.
  • Wikidata covered cities, authors and sports clubs well. Other types were filled in from Arabic CommonCrawl using 5–10 hand-written patterns per type, followed by manual filtering and annotation.
  • Generated stories tied Arab names to poverty and traditionalism. NER was more accurate on Western entities, and sentiment models linked Arab entities more often to negative polarity.
  • In infilling, models preferred Western entities even in Arab-specific contexts. The paper's illustration reports 64% Western preference.
  • Among the six corpora, Wikipedia scored as more Western-biased, plausibly because much of its content is translated. Local news and Twitter/X had the lowest bias score (CBS). Sentences with English-like Arabic syntax also triggered more Western bias.

Interesting ideas

  • I1. The authors deliberately built the evaluation set without any LM (Wikidata plus pattern matching), so the benchmark cannot inherit the biases of the systems it tests.
  • I2. Real sentences have one entity slot masked, and the slot is filled from two contrasting entity lists, giving minimal pairs where only the entity's cultural origin changes.
  • I3. The bias score counts, over every context and every Arab–Western entity pair, how often the model rates the Western option more likely. This turns preference into a single pairwise statistic that is easy to interpret.
  • I4. Corpora are compared by training a cheap n-gram LM on each and scoring it on the benchmark, a lightweight way to rank data sources before expensive training.
  • I5. Prompts are split by grammatical gender so that every filled-in slot still agrees with the verbs around it, which keeps the test sentences well-formed.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): Test sets used to judge LLM teacher tiers should be assembled from patterns and treebanks rather than by the teacher itself, so they work as genuinely independent negative controls.
  • I2 (answer): Swapping character names or objects in fable QA items and checking that answers stay the same would show whether readers rely on the story's structure rather than on entity identity.
  • I3 (world): The same pairwise count could audit defaults in the knowledge graph or ontology, for example which filler the world model picks for an unspecified drink or meal.
  • I4 (learn): Candidate raw text for silver parsing could be ranked the same way, scoring each source against a target domain such as school texts or tales before committing parser time.
  • I5 (back): When generation fills a slot in a template, it should check agreement constraints such as pronoun gender and number so that substitutions never produce ungrammatical output.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Georgia Institute of TechnologyAtlanta · United States133 works · 24,497 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSocial Sciences · 1,772 worksSafety Research · 543 works

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 3,320 worksSemitic languages · 2,908 worksBias, fairness & safety · 517 works

Cite

Cite as Tarek Naous, Michael J Ryan, Alan Ritter and Wei Xu. 2024. Having Beer after Prayer? Measuring Cultural Bias in Large Language Models. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.acl-long.862

@inproceedings{naous2024having,
  title = {{Having Beer after Prayer? Measuring Cultural Bias in Large Language Models}},
  author = {Tarek Naous, Michael J Ryan, Alan Ritter and Wei Xu},
  booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2024},
  doi = {10.18653/v1/2024.acl-long.862},
  url = {https://doi.org/10.18653/v1/2024.acl-long.862}
}

References

111 references, 51 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ahmed Abdelali, Kareem Darwish, Nadir Durrani, and Hamdy Mubarak. 2016. Farasa: A fast and furious segmenter for arabic. In Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: Demonstrations, pages 11–16.
  2. Muhammad Abdul-Mageed, AbdelRahim Elmadany, et al. 2021. ARBERT & MARBERT: Deep bidirectional transformers for arabic. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7088–7105. ↗
  3. Marwa Abdulhai, Gregory Serapio-Garcia, Clément Crepy, Daria Valter, John Canny, and Natasha Jaques. 2023. Moral foundations of large language models. arXiv preprint arXiv:2310.15337. ↗
  4. Abubakar Abid, Maheen Farooqi, and James Zou. 2021a. Large language models associate muslims with violence. Nature Machine Intelligence, 3(6):461–463. ↗
  5. Abubakar Abid, Maheen Farooqi, and James Zou. 2021b. Persistent anti-muslim bias in large language models. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, AIES ’21, page 298–306, New York, NY, USA. Association for Computing Machinery.
  6. Jaimeen Ahn and Alice Oh. 2021. Mitigating language-dependent ethnic bias in BERT. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 533–549, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. ↗
  7. Kabir Ahuja, Rishav Hada, Millicent Ochieng, Prachi Jain, Harshita Diddee, Samuel Maina, Tanuja Ganu, Sameer Segal, Maxamed Axmed, Kalika Bali, et al. 2023. Mega: Multilingual evaluation of generative ai. arXiv preprint arXiv:2303.12528. ↗
  8. Haozhe An, Zongxia Li, Jieyu Zhao, and Rachel Rudinger. 2023. SODAPOP: Open-ended discovery of social biases in social commonsense reasoning models. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1565–1588. find
  9. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. AraBERT: Transformer-based model for arabic language understanding. In LREC Workshop Language Resources and Evaluation Conference 11–16 May 2020, page 9. ↗
  10. Wissam Antoun, Fady Baly, and Hazem Hajj. 2021. AraGPT2: Pre-trained transformer for arabic language generation. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 196– 207. ↗
  11. Arnav Arora, Lucie-Aimée Kaffee, and Isabelle Augenstein. 2023. Probing pre-trained language models for cross-cultural differences in values. In Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP), pages 114–130.
  12. Parishad BehnamGhader and Aristides Milios. 2022. An analysis of social biases present in BERT variants across multiple languages. In Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS 2022. ↗
  13. Yassine Benajiba, Paolo Rosso, and José Miguel Benedíruiz. 2007. Anersys: An arabic named entity recognition system based on maximum entropy. In Computational Linguistics and Intelligent Text Processing: 8th International Conference, CICLing 2007, Mexico City, Mexico, February 18-24, 2007. Proceedings 8, pages 143–153. Springer. find
  14. Jayadev Bhaskaran and Isha Bhallamudi. 2019. Good secretaries, bad truck drivers? occupational gender stereotypes in sentiment analysis. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 62–68, Florence, Italy. Association for Computational Linguistics. find
  15. Shaily Bhatt, Sunipa Dev, Partha Talukdar, Shachi Dave, and Vinodkumar Prabhakaran. 2022. Re-contextualizing fairness in nlp: The case of india. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 727–740. ↗
  16. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  17. Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334):183–186. ↗
  18. Yang Cao, Anna Sotnikova, Hal Daumé III, Rachel Rudinger, and Linda Zou. 2022a. Theory-grounded measurement of us social stereotypes in english language models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1276–1295. find
  19. Yang Trista Cao, Anna Sotnikova, Hal Daumé III, Rachel Rudinger, and Linda Zou. 2022b. Theory-grounded measurement of U.S. social stereotypes in English language models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1276–1295, Seattle, United States. Association for Computational Linguistics. ↗
  20. Dipto Das, Shion Guha, and Bryan Semaan. 2023. Toward cultural bias evaluation datasets: The case of bengali gender, religious, and national identity. In Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP), pages 68–83. find
  21. David L. Davies and Donald W. Bouldin. 1979. A cluster separation measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-1(2):224– 227. ↗
  22. Sunipa Dev, Tao Li, Jeff M Phillips, and Vivek Srikumar. 2021. OSCaR: Orthogonal subspace correction and rectification of biases in word embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5034–5050. find
  23. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186. ↗
  24. Esin Durmus, Karina Nyugen, Thomas I Liao, Nicholas Schiefer, Amanda Askell, Anton Bakhtin, Carol Chen, Zac Hatfield-Dodds, Danny Hernandez, Nicholas Joseph, et al. 2023. Towards measuring the representation of subjective global opinions in language models. arXiv preprint arXiv:2306.16388. ↗
  25. Ibrahim Abu El-Khair. 2016. 1.5 billion words Arabic corpus. arXiv preprint arXiv:1611.04033. ↗
  26. Yong Cao, Li Zhou, Seolhwa Lee, Laura Cabello, Min Chen, and Daniel Hershcovich. 2023. Assessing cross-cultural alignment between ChatGPT and human societies: An empirical study. In Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP), pages 53–67.
  27. AbdelRahim Elmadany, ElMoatez Billah Nagoudi, and Muhammad Abdul-Mageed. 2023. ORCA: A challenging benchmark for Arabic language understanding. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9559–9586, Toronto, Canada. Association for Computational Linguistics.
  28. Laura Chiticariu, Yunyao Li, and Frederick R. Reiss. 2013. Rule-based information extraction is dead! long live rule-based information extraction systems! In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 827–832, Seattle, Washington, USA. Association for Computational Linguistics. find
  29. Ashraf Elnagar, Yasmin S Khalifa, and Anas Einea. 2018. Hotel arabic-reviews dataset construction for sentiment analysis applications. Intelligent natural language processing: Trends and applications, pages 35–52. ↗
  30. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Édouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8440–8451. find
  31. Paula Czarnowska, Yogarshi Vyas, and Kashif Shah. 2021. Quantifying social biases in nlp: A generalization and empirical comparison of extrinsic fairness metrics. Transactions of the Association for Computational Linguistics, 9:1249–1267. ↗
  32. Shangbin Feng, Chan Young Park, Yuhan Liu, and Yulia Tsvetkov. 2023. From pretraining data to language models to downstream tasks: Tracking the trails of political biases leading to unfair nlp models. arXiv preprint arXiv:2305.08283. ↗
  33. Kathleen C Fraser, Svetlana Kiritchenko, and Esma Balkir. 2022. Does moral code have a moral code? probing delphi’s moral philosophy. In Proceedings of the 2nd Workshop on Trustworthy Natural Language Processing (TrustNLP 2022), pages 26–42. ↗
  34. Dayne Freitag, John Cadigan, Robert Sasseen, and Paul Kalmar. 2022. Valet: Rule-based information extraction for rapid deployment. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 524–533, Marseille, France. European Language Resources Association. find
  35. Isabel O Gallegos, Ryan A Rossi, Joe Barrow, Md Mehrab Tanjim, Sungchul Kim, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, and Nesreen K Ahmed. 2023. Bias and fairness in large language models: A survey. arXiv preprint arXiv:2309.00770. ↗
  36. Adriano Gómez-Bantel. 2018. Football clubs as symbols of regional identities. In Football, Community and Sustainability, pages 32–42. Routledge. ↗
  37. Jesse Graham, Brian A Nosek, Jonathan Haidt, Ravi Iyer, Spassena Koleva, and Peter H Ditto. 2011. Mapping the moral domain. Journal of personality and social psychology, 101(2):366. ↗
  38. Valeschka M Guerra and Roger Giner-Sorolla. 2010. The community, autonomy, and divinity scale (cads): A new tool for the cross-cultural study of morality. Journal of cross-cultural psychology, 41(1):35–50. ↗
  39. Wei Guo and Aylin Caliskan. 2021. Detecting emergent intersectional biases: Contextualized word embeddings contain a distribution of human-like biases. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pages 122–133. find
  40. Christian Haerpfer, Ronald Inglehart, Alejandro Moreno, Christian Welzel, Kseniya Kizilova, Jaime Diez-Medrano, Marta Lagos, Pippa Norris, E Ponarin, and B Puranen. 2021. World values survey: Round seven. JD Systems Institute & WVSA Secretariat. Data File Version, 2(0). find
  41. Katharina Hämmerl, Björn Deiseroth, Patrick Schramowski, Jindřich Libovickỳ, Constantin A Rothkopf, Alexander Fraser, and Kristian Kersting. 2022. Speaking multiple languages affects the moral bias of language models. arXiv preprint arXiv:2211.07733. ↗
  42. Jochen Hartmann, Jasper Schwenzow, and Maximilian Witte. 2023. The political ideology of conversational ai: Converging evidence on chatgpt’s pro-environmental, left-libertarian orientation. arXiv preprint arXiv:2301.01768. ↗
  43. Babak Hemmatian, Razan Baltaji, and Lav R Varshney. 2023. Muslim-violence bias persists in debiased gpt models. arXiv preprint arXiv:2310.18368. ↗
  44. Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, et al. 2022. Challenges and strategies in cross-cultural nlp. In 60th Annual Meeting of the Association-for-Computational-Linguistics (ACL), MAY 22-27, 2022, Dublin, IRELAND, pages 6997–7013. Association for Computational Linguistics. ↗
  45. Geert Hofstede. 1984. Culture’s consequences: International differences in work-related values, volume 5. Sage. find
  46. Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  47. Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Dingjie Song, Zhihong Chen, Abdulmohsen Alharthi, Bang An, Ziche Liu, et al. 2023. AceGPT, localizing large language models in Arabic. arXiv preprint arXiv:2309.12053. ↗
  48. Jing Huang and Diyi Yang. 2023. Culturally aware natural language inference. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7591–7609. ↗
  49. Go Inoue, Bashar Alhafni, Nurpeiis Baimukan, Houda Bouamor, and Nizar Habash. 2021. The interplay of variant, size, and task type in arabic pre-trained language models. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 92– 104.
  50. Rebecca L Johnson, Giada Pistilli, Natalia Menédez-González, Leslye Denisse Dias Duran, Enrico Panai, Julija Kalpokiene, and Donald Jay Bertulfo. 2022. The Ghost in the Machine has an American accent: value conflict in GPT-3. arXiv preprint arXiv:2203.07785. ↗
  51. Masahiro Kaneko and Danushka Bollegala. 2022. Unmasking the mask–evaluating social biases in masked language models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 11954–11962. ↗
  52. Masahiro Kaneko, Aizhan Imankulova, Danushka Bollegala, and Naoaki Okazaki. 2022. Gender bias in masked language models for multiple languages. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2740–2750, Seattle, United States. Association for Computational Linguistics. ↗
  53. Amr Keleg and Walid Magdy. 2023. DLAMA: A framework for curating culturally diverse facts for probing the knowledge of pretrained language models. arXiv preprint arXiv:2306.05076. ↗
  54. Alex Koch, Roland Imhoff, Ron Dotsch, Christian Unkelbach, and Hans Alves. 2016. The abc of stereotypes about groups: Agency/socioeconomic success, conservative–progressive beliefs, and communion. Journal of personality and social psychology, 110(5):675. ↗
  55. Mascha Kurpicz-Briki. 2020. Cultural differences in bias? origin and gender bias in pre-trained german and french word embeddings. find
  56. Wuwei Lan, Yang Chen, Wei Xu, and Alan Ritter. 2020. An empirical study of pre-trained transformers for arabic information extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4727–4734.
  57. Anne Lauscher and Goran Glavaš. 2019. Are we consistently biased? multidimensional analysis of biases in distributional word vectors. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics, pages 85–91, Minneapolis, Minnesota. Association for Computational Linguistics. find
  58. Nayeon Lee, Chani Jung, and Alice Oh. 2023. Hate speech classifiers are culturally insensitive. In Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP), pages 35–46. find
  59. Sharon Levy, Neha Anna John, Ling Liu, Yogarshi Vyas, Jie Ma, Yoshinari Fujinuma, Miguel Ballesteros, Vittorio Castelli, and Dan Roth. 2023. Comparing biases and the impact of multilingual training across multiple languages. arXiv preprint arXiv:2305.11242. ↗
  60. Yingji Li, Mengnan Du, Rui Song, Xin Wang, and Ying Wang. 2023. A survey on fairness in large language models. arXiv preprint arXiv:2308.10149. ↗
  61. Weicheng Ma, Brian Chiang, Tong Wu, Lili Wang, and Soroush Vosoughi. 2023a. Intersectional stereotypes in large language models: Dataset and analysis. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8589–8597. find
  62. Weicheng Ma, Henry Scheible, Brian Wang, Goutham Veeramachaneni, Pratim Chowdhary, Alan Sun, Andrew Koulogeorge, Lili Wang, Diyi Yang, and Soroush Vosoughi. 2023b. Deciphering stereotypes in pre-trained language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11328–11345. find
  63. Marta Marchiori Manerba, Karolina Stańczak, Riccardo Guidotti, and Isabelle Augenstein. 2023. Social bias probing: Fairness benchmarking for language models. arXiv preprint arXiv:2311.09090. ↗
  64. Reem I Masoud, Ziquan Liu, Martin Ferianc, Philip Treleaven, and Miguel Rodrigues. 2023. Cultural alignment in large language models: An explanatory analysis based on hofstede’s cultural dimensions. arXiv preprint arXiv:2309.12342. ↗
  65. Chandler May, Alex Wang, Shikha Bordia, Samuel Bowman, and Rachel Rudinger. 2019. On measuring social biases in sentence encoders. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 622–628.
  66. Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2022. Rethinking the role of demonstrations: What makes in-context learning work? In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11048–11064.
  67. Massimo Montanari. 2006. Food is culture. Columbia University Press. find
  68. Moin Nadeem, Anna Bethke, and Siva Reddy. 2021a. Stereoset: Measuring stereotypical bias in pretrained language models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5356–5371.
  69. Moin Nadeem, Anna Bethke, and Siva Reddy. 2021b. StereoSet: Measuring stereotypical bias in pretrained language models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5356–5371, Online. Association for Computational Linguistics.
  70. Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R. Bowman. 2020a. CrowS-pairs: A challenge dataset for measuring social biases in masked language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1953–1967, Online. Association for Computational Linguistics.
  71. Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R Bowman. 2020b. Crows-pairs: A challenge dataset for measuring social biases in masked language models. arXiv preprint arXiv:2010.00133. ↗
  72. Aurélie Névéol, Yoann Dupont, Julien Bezançon, and Karën Fort. 2022. French CrowS-pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8521–8531, Dublin, Ireland. Association for Computational Linguistics.
  73. Tuan-Phong Nguyen, Simon Razniewski, Aparna Varde, and Gerhard Weikum. 2023. Extracting cultural commonsense knowledge at scale. In Proceedings of the ACM Web Conference 2023, pages 1907–1917. find
  74. Debora Nozza, Federico Bianchi, and Dirk Hovy. 2021. HONEST: Measuring hurtful sentence completion in language models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2398–2406, Online. Association for Computational Linguistics.
  75. Debora Nozza, Federico Bianchi, Anne Lauscher, and Dirk Hovy. 2022. Measuring harmful sentence completion in language models for LGBTQIA+ individuals. In Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion, pages 26–34, Dublin, Ireland. Association for Computational Linguistics. find
  76. Shramay Palta and Rachel Rudinger. 2023. FORK: A bite-sized test set for probing culinary cultural biases in commonsense reasoning models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9952–9962. ↗
  77. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1):5485–5551. ↗
  78. Aida Ramezani and Yang Xu. 2023. Knowledge of cultural moral norms in large language models. arXiv preprint arXiv:2306.01857. ↗
  79. Brian Roark, Richard Sproat, Cyril Allauzen, Michael Riley, Jeffrey Sorensen, and Terry Tai. 2012. The opengrm open-source finite-state grammar software libraries. In Proceedings of the ACL 2012 System Demonstrations, pages 61–66. find
  80. Candace Ross, Boris Katz, and Andrei Barbu. 2021. Measuring social biases in grounded vision and language embeddings. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 998–1008. find
  81. Julian Salazar, Davis Liang, Toan Q Nguyen, and Katrin Kirchhoff. 2020. Masked language model scoring. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2699–2712.
  82. Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto. 2023. Whose opinions do language models reflect? arXiv preprint arXiv:2303.17548. ↗
  83. Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, et al. 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100. ↗
  84. Patrick Schramowski, Cigdem Turan, Nico Andersen, Constantin A Rothkopf, and Kristian Kersting. 2022. Large pre-trained language models contain human-like biases of what is right and wrong to do. Nature Machine Intelligence, 4(3):258–268. ↗
  85. Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, Satheesh Katipomu, Haonan Li, Fajri Koto, Osama Mohammed Afzal, Samta Kamboj, Onkar Pandit, Rahul Pal, et al. 2023. Jais and jais-chat: Arabic-centric foundation and instruction-tuned open generative large language models. arXiv preprint arXiv:2308.16149. ↗
  86. Emily Sheng, Kai-Wei Chang, Prem Natarajan, and Nanyun Peng. 2021. Societal biases in language generation: Progress and challenges. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4275–4293. ↗
  87. Vered Shwartz. 2022. Good night at 4 pm?! time expressions in different cultures. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2842–2853. ↗
  88. Karolina Stanczak and Isabelle Augenstein. 2021. A survey on gender bias in natural language processing. arXiv preprint arXiv:2112.14168. ↗
  89. Pedro Javier Ortiz Suárez, Benoît Sagot, and Laurent Romary. 2019. Asynchronous pipeline for processing huge corpora on medium to low resource infrastructures. In 7th Workshop on the Challenges in the Management of Large Corpora (CMLC-7). Leibniz-Institut für Deutsche Sprache. find
  90. Magdalena Szumilas. 2010. Explaining odds ratios. Journal of the Canadian academy of child and adolescent psychiatry, 19(3):227. find
  91. Fatjri Nur Tajuddin. 2018. Cultural and social identity in clothing matters “different cultures, different meanings”. European Journal of Behavioral Sciences, 1(4):21–25. find
  92. Zeerak Talat, Aurélie Névéol, Stella Biderman, Miruna Clinciu, Manan Dey, Shayne Longpre, Sasha Luccioni, Maraim Masoud, Margaret Mitchell, Dragomir Radev, Shanya Sharma, Arjun Subramonian, Jaesung Tae, Samson Tan, Deepak Tunuguntla, and Oskar Van Der Wal. 2022. You reap what you sow: On the challenges of bias evaluation under multilingual settings. In Proceedings of BigScience Episode #5 – Workshop on Challenges & Perspectives in Creating Large Language Models, pages 26–41, virtual+Dublin. Association for Computational Linguistics.
  93. Yi Chern Tan and L Elisa Celis. 2019. Assessing social and intersectional biases in contextualized word representations. Advances in neural information processing systems, 32. ↗
  94. Brian Thompson, Mehak Preet Dhaliwal, Peter Frisch, Tobias Domhan, and Marcello Federico. 2024. A shocking amount of the web is machine translated: Insights from multi-way parallelism. arXiv preprint arXiv:2401.05749. ↗
  95. Samia Touileb, Lilja Øvrelid, and Erik Velldal. 2022. Occupational biases in Norwegian and multilingual language models. In Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 200–211, Seattle, Washington. Association for Computational Linguistics. find
  96. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288. ↗
  97. Ahmet Üstün, Viraat Aryabumi, Zheng-Xin Yong, Wei-Yin Ko, Daniel D’souza, Gbemileke Onilude, Neel Bhandari, Shivalika Singh, Hui-Lee Ooi, Amr Kayid, et al. 2024. Aya model: An instruction finetuned open-access multilingual language model. arXiv preprint arXiv:2402.07827. ↗
  98. Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-sne. Journal of machine learning research, 9(11). find
  99. Aniket Vashishtha, Kabir Ahuja, and Sunayana Sitaram. 2023. On evaluating and mitigating gender biases in multilingual settings. In Findings of the Association for Computational Linguistics: ACL 2023, pages 307–318. find
  100. Pranav Narayanan Venkit, Sanjana Gautam, Ruchi Panchanadikar, Ting-Hao Huang, and Shomir Wilson. 2023. Nationality bias in text generation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 116–122. ↗
  101. Denny Vrandečić and Markus Krötzsch. 2014. Wikidata: a free collaborative knowledgebase. Communications of the ACM, 57(10):78–85.
  102. Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, and Nanyun Peng. 2023. “kelly is a warm person, joseph is a role model”: Gender biases in llm-generated reference letters. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3730–3748. integration into the CLARIN-infrastructure. In Proceedings of the fourth arabic natural language processing workshop, pages 175–182.
  103. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2018. Gender bias in coreference resolution: Evaluation and debiasing methods. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 15–20, New Orleans, Louisiana. Association for Computational Linguistics. ↗
  104. Xuhui Zhou, Maarten Sap, Swabha Swayamdipta, Yejin Choi, and Noah Smith. 2021. Challenges in automated debiasing for toxic language detection. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3143–3155, Online. Association for Computational Linguistics. ↗
  105. Shuhe Wang, Xiaofei Sun, Xiaoya Li, Rongbin Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, and Guoyin Wang. 2023a. GPT-NER: Named entity recognition via large language models. arXiv preprint arXiv:2304.10428. ↗
  106. Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, Ruyi Dai, Jen-tse Huang, Zhaopeng Tu, and Michael R Lyu. 2023b. Not all countries celebrate thanksgiving: On the cultural dominance in large language models. arXiv preprint arXiv:2310.12481. ↗
  107. Chunpu Xu, Steffi Chern, Ethan Chern, Ge Zhang, Zekun Wang, Ruibo Liu, Jing Li, Jie Fu, and Pengfei Liu. 2023. Align on the fly: Adapting chatbot behavior to established norms. arXiv preprint arXiv:2312.15907. ↗
  108. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 483–498. ↗
  109. Da Yin, Hritik Bansal, Masoud Monajatipoor, Liunian Harold Li, and Kai-Wei Chang. 2022. GeoM-LAMA: Geo-diverse commonsense probing on multilingual pre-trained language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2039–2055. find
  110. Zheng-Xin Yong, Hailey Schoelkopf, Niklas Muennighoff, Alham Fikri Aji, David Ifeoluwa Adelani, Khalid Almubarak, M Saiful Bari, Lintang Sutawika, Jungo Kasai, Ahmed Baruwa, et al. 2022. Bloom+1: Adding language support to bloom for zero-shot prompting. arXiv preprint arXiv:2212.09535. ↗
  111. Imad Zeroual, Dirk Goldhahn, Thomas Eckart, and Abdelhak Lakhouaja. 2019. OSIAN: Open source international Arabic news corpus-preparation and find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/naous-2024-having-beer-after-prayer-measuring/