The DOI matches its Crossref record, with a small difference in title or year; 44 of the 44 references it cites were found in a registry or an index.
Cultural Bias in Large Language Models: A Comprehensive Analysis and Mitigation Strategies
Open accessAbstract
This paper delves into the intricate relationship between Large Language Models (LLMs) and cultural bias. It underscores the significant impact LLMs can have on shaping a more equitable and culturally sensitive digital landscape, while also addressing the challenges that arise when integrating these powerful AI tools. The paper emphasizes the immense significance of LLMs in contemporary AI research and applications, underpinning many systems and algorithms. However, their potential role in perpetuating or mitigating cultural bias remains a pressing issue warranting extensive analysis. Cultural bias stems from various intertwined factors; the following analysis categorizes cultural bias shaping LLMs into three dimensions: data quality, algorithm design, and user interaction dynamics. Furthermore, the impacts of LLMs on cultural identity and linguistic diversity are scrutinized, highlighting the interplay between technology and culture. The paper advocates responsible AI development, outlining mitigation strategies such as ethical guidelines, diverse training data, user feedback mechanisms, and transparency measures. In conclusion, the paper emphasizes that cultural bias in LLMs is not solely a problem but also presents an opportunity. It can enhance our awareness and critical understanding of our own cultural biases while fostering curiosity and respect for diverse cultural perspectives.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“AI systems are trained on extensive datasets that may harbor cultural biases (86, 89, 90), which can inadvertently manifest in the historical information presented on cards.”
From Global Health Trade Summit: an AI-enhanced simulation of international trade and global health for undergraduate public health education (2025) · cites this paper as [89]
Citations
Cites
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 3×
“Typically trained on vast amounts of uncurated Internet-based data, LLMs inherit stereotypes, misrepresentations, derogatory language, and other harmful behaviors that disproportionately a ff ect already-vulnerable and marginalized communities (Bender et al. 2021; Dodge et al. 2021).”
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050 · cited 2×
“LLMs can inherit harmful and stereotypical language from their training data, leading to downstream representational harms (Blodgett et al., 2020).”
LaMDA: Language Models for Dialog Applications
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T., Baker, L., Du, Y., et al. (2022) · arXiv · doi:10.48550/arxiv.2201.08239 · Cited by 778
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Gehman, S., Gururangan, S., Sap, M., Choi, Y., & Smith, N. A. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.301 · Cited by 693
Evidence that gendered wording in job advertisements exists and sustains gender inequality.
Gaucher, D., Friesen, J., & Kay, A. C. (2011) · Journal of Personality and Social Psychology · doi:10.1037/a0022530 · Cited by 687
Measuring and Mitigating Unintended Bias in Text Classification
Dixon, L., Li, J., Sorensen, J., Thain, N., & Vasserman, L. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278729 · Cited by 674
StereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2021) · 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) · doi:10.18653/v1/2021.acl-long.416 · Cited by 643
Race after technology Abolitionist tools for the new Jim code
Benjamin, R. (2019) · Cited by 569
Research works printed but not linked: 6
- Chang, E. Y. (2024). SocraSynth: Multi-LLM Reasoning with Conditional Statistics. arXiv preprint arXiv:2402.06634. · arXiv
- Dev, S., Goyal, J., Tewari, D., Dave, S., & Prabhakaran, V. (2023). Building socio-culturally inclusive stereotype resources with community engagement. arXiv:2307.10514. · arXiv
- Lee, M. H., Montgomery, J. M., & Lai, C. K. (2024). The effect of group status on the variability of group representations in LLM-generated text. arXiv preprint arXiv:2401.08495. · arXiv
- Orgad, H., & Belinkov, Y. (2022). BLIND: Bias removal with no demographics. arXiv preprint arXiv:2212.10563. · arXiv
- Tao, Y., Viberg, O., Baker, R. S., & Kizilcec, R. F. (2023). Auditing and mitigating cultural bias in llms. arXiv preprint arXiv:2311.14096. · arXiv
- Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., Bikel, D., Blecher, L., Canton Ferrer, C., Chen, M., Cucurull, G., Esiobu, D., Fernandes, J., Fu, J., Fu, W., ... Scialom, T. (2023). Llama 2: Open Foundation and Fine-tuned Chat Models. arXiv preprint arXiv:2307.09288. · arXiv
Cited by
Agentic AI in Education: State of the Art and Future Directions
Kostopoulos, G., Gkamas, V., Rigou, M., & Kotsiantis, S. (2025) · IEEE Access · doi:10.1109/access.2025.3620473 · Cited by 69
The Importance of AI Data Governance in Large Language Models
(2025) · doi:10.3390/bdcc9060147 · Cited by 58
Logical and Physical Optimizations for SQL Query Execution over Large Language Models
Satriani, D., Veltri, E., Santoro, D., Rosato, S., Varriale, S., & Papotti, P. (2025) · Proceedings of the ACM on Management of Data · doi:10.1145/3725411 · Cited by 8
Selective agreement, not sycophancy: investigating opinion dynamics in LLM interactions
Cau, E., Pansanella, V., Pedreschi, D., & Rossetti, G. (2025) · EPJ Data Science · doi:10.1140/epjds/s13688-025-00579-1 · Cited by 9
“LLMs have been proven to exhibit societal and cultural biases [62–64] attributable to the training data, algorithm structure, and user interactions [65], with an alignment with Western cultural values, especially when prompted in English [66, 67].”
Gautam, S., Chandra, M., De, A., Chakravorti, T., Malik, G., & De Choudhury, M. (2025) · arXiv · doi:10.48550/arxiv.2508.06849 · Cited by 7
Metadata
- Authors
- Liu, Z.
- Affiliations
- Shanghai University (CN)
- Corresponding author
- Liu, Zhaoming
- ORCID
- Liu, Zhaoming
- Venue
- Journal of Transcultural Communication
- Publisher
- Walter de Gruyter GmbH
- Published
- 2023-12-01
- Volume
- 3
- Issue
- 2
- Pages
- 224-244
- ISSN
- 2749-4799 (ISSN-L)
- OpenAlex
- W4402811079
- Cited by
- 77
- References
- 44
- Citations by year
- 2026: 41 · 2025: 34 · 2024: 2
- FWCI
- 19.21
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Journal of Transcultural Communication (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Keywords
- cultural bias, large language models, bias mitigation, training data quality, algorithm design, user interaction, cultural identity, linguistic diversity, responsible AI, moral norms, user feedback, transparency, cultural sensitivity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Cultural Bias in Large Language Models: A Comprehensive Analysis and Mitigation Strategies. https://app.cochat.ai/papers/10.1515/jtc-2023-0019
- The paper
- Liu, Z. (2025). Cultural Bias in Large Language Models: A Comprehensive Analysis and Mitigation Strategies. Journal of Transcultural Communication. https://doi.org/10.1515/jtc-2023-0019
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.