---
title: "Can Persona-Prompted LLMs Emulate Subgroup Values? An"
description: "The authors define subgroups by sex, age, ethnicity and religion, alone and in pairs. 17.4 points. 48 references."
authors: ["Bryan Chen Zhengyu Tan", "Zhengyuan Liu", "Xiaoyuan Yi", "Jing Yao", "Xing Xie", "Nancy F. Chen", "Roy Ka-Wei Lee"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1127/"
doi: "10.18653/v1/2026.acl-long.1127"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/tan-2026-can-persona-prompted-llms-emulate/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tan-2026-can-persona-prompted-llms-emulate/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/) / Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

# Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

**Authors:** [Bryan Chen Zhengyu Tan](https://md.research.elamur.ai/free/en/authors/bryan-chen-zhengyu-tan/), [Zhengyuan Liu](https://md.research.elamur.ai/free/en/authors/zhengyuan-liu/), [Xiaoyuan Yi](https://md.research.elamur.ai/free/en/authors/xiaoyuan-yi/), Jing Yao, [Xing Xie](https://md.research.elamur.ai/free/en/authors/xing-xie/), [Nancy F. Chen](https://md.research.elamur.ai/free/en/authors/nancy-chen/) and [Roy Ka-Wei Lee](https://md.research.elamur.ai/free/en/authors/roy-ka-wei-lee/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1127/) · [PDF](https://aclanthology.org/2026.acl-long.1127.pdf) · [DOI 10.18653/v1/2026.acl-long.1127](https://doi.org/10.18653/v1/2026.acl-long.1127) · [OpenAlex](https://openalex.org/W7166805011)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary

Most LLMs are aligned to a single, aggregated value profile that often leans Western. This paper asks whether models can instead reproduce the differing values of demographic subgroups within one society. Singapore serves as the testbed, using its World Values Survey (WVS) Wave 7 data. The authors define subgroups by sex, age, ethnicity and religion, alone and in pairs. They introduce a Modal Diversity Score to show which questions divide subgroups and which they agree on. From this they build a dataset of more than 20,000 persona-conditioned samples.

Even GPT-4.1 predicts the most common answer of a prompted subgroup poorly. Plain supervised fine-tuning (SFT) on numerical survey answers substantially improves accuracy on intersectional subgroups never seen in training, and the gains partly carry over to open-ended answers.

The fairness analysis is less encouraging. Base models already serve some personas better than others, and SFT widens these gaps on distance-aware metrics. The authors conclude that subgroup-level alignment is feasible but needs explicit attention to fairness.

## Key points

- **Data:** Singapore WVS Wave 7 with 2,012 respondents, filtered to 214 questions and 98 subgroups. A subgroup's answer to a question counts only if at least 30 people in that subgroup responded.
- **Out-of-distribution split:**
  - Training uses 50 subgroups (about 10,700 samples): single axes plus sex×age, sex×ethnicity and sex×religion.
  - Evaluation uses 48 unseen subgroups (10,177 samples): age×religion, age×ethnicity and ethnicity×religion.
- **Accuracy:** GPT-4.1 reaches only 57.4% on subgroup modal answers. SFT adds 17.4 points on average for unseen subgroups. Examples:
  - Sailor2: 35.6% → 72.0%
  - Llama-3.1: 51.4% → 68.5%
  - SEA-LION: 53.0% → 64.2%
- **Bias:** Models emulate young, male, Chinese and Christian personas better than older, female, Malay and Muslim ones. The normalised range of subgroup performance grows from 0.280 to 0.336 after SFT.
- **Limitations noted by the authors:**
  - The supervision target is the subgroup's modal answer, which ignores disagreement within a subgroup.
  - Only SFT is tested; DPO and GRPO are left for future work.
  - Possible WVS contamination in pre-training data is judged unlikely to explain the results.

*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

- [Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) — Company, Redmond, United States · 378 works · 161,630 citations
- [Agency for Science, Technology and Research](https://md.research.elamur.ai/free/en/government/agency-for-science-technology-and-research/) — Government body, Singapore, Singapore · 31 works · 14,235 citations

Also on the byline: [CNRS@CREATE Ltd](https://ror.org/03hjh0h14).

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Safety Research](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · 626 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 587 works

## Cite

Cite as: Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen and Roy Ka-Wei Lee. 2026. Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment. Proceedings of the 64th 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.

```bibtex
@inproceedings{tan2026can,
  title = {{Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment}},
  author = {Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen and Roy Ka-Wei Lee},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1127},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1127}
}
```

- [← previous Can Multi-agent Help Disambiguation in Multi-domain Translation?](https://md.research.elamur.ai/free/en/papers/man-2026-can-multi-agent-help-disambiguation/)
- [next → Can Small LLMs Learn a Robust Theory of Mind via RLVR? Investigating Generalization through the False-Belief Task](https://md.research.elamur.ai/free/en/papers/sarangi-2026-can-small-llms-learn-robust/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/)

## References

48 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Gati Aher, Rosa I. Arriaga, and Adam Tauman Kalai. 2023. Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies. [find](https://scholar.google.com/scholar?q=Gati+Aher%2C+Rosa+I%2E+Arriaga%2C+and+Adam+Tauman+Kalai%2E+2023%2E+Using+Large+Language+Models+to+Simulate+Multiple+Humans+and+Replicate+Human+Subject+Studies%2E)
2. Jacy Reese Anthis, Ryan Liu, Sean M. Richardson, Austin C. Kozlowski, Bernard Koch, Erik Brynjolfsson, James Evans, and Michael S. Bernstein. 2025. Position: LLM social simulations are a promising research method. In Forty-Second International Conference on Machine Learning Position Paper Track. [find](https://scholar.google.com/scholar?q=Jacy+Reese+Anthis%2C+Ryan+Liu%2C+Sean+M%2E+Richardson%2C+Austin+C%2E+Kozlowski%2C+Bernard+Koch%2C+Erik+Brynjolfsson%2C+James+Evans%2C+and+Michael+S%2E+Bernstein%2E+2025%2E+Position%3A+LLM+social+simulations+are+a+promising+res)
3. Anne Arzberger, Stefan Buijsman, Maria Luce Lupetti, Alessandro Bozzon, and Jie Yang. 2024. Nothing comes without its world – practical challenges of aligning LLMs to situated human values through RLHF. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 7(1):61–73. [find](https://scholar.google.com/scholar?q=Anne+Arzberger%2C+Stefan+Buijsman%2C+Maria+Luce+Lupetti%2C+Alessandro+Bozzon%2C+and+Jie+Yang%2E+2024%2E+Nothing+comes+without+its+world+%E2%80%93+practical+challenges+of+aligning+LLMs+to+situated+human+values+through+RLH)
4. Yejin Bang, Delong Chen, Nayeon Lee, and Pascale Fung. 2024. [Measuring political bias in large language models: What is said and how it is said](https://md.research.elamur.ai/free/en/papers/bang-2024-measuring-political-bias-large-language/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11142–11159, Bangkok, Thailand. A…
5. Su Lin Blodgett, Solon Barocas, Hal Daumé III, and Hanna Wallach. 2020. [Language (Technology) is Power: A Critical Survey of “Bias” in NLP](https://md.research.elamur.ai/free/en/papers/blodgett-2020-language-technology-is-power-critical/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5454– 5476, Online. Association for Computational Linguistics.
6. Osmond Chia. 2025. Landmark singapore study flags racial, cultural, gender biases in AI models. The Straits Times. [find](https://scholar.google.com/scholar?q=Osmond+Chia%2E+2025%2E+Landmark+singapore+study+flags+racial%2C+cultural%2C+gender+biases+in+AI+models%2E+The+Straits+Times%2E)
7. Kimberlé Crenshaw. 1989. Demarginalizing the intersection of race and sex: A black feminist critique of antidiscrimination doctrine, feminist theory and antiracist politics. University of Chicago Legal Forum, 1989(1):139–167. [find](https://scholar.google.com/scholar?q=Kimberl%C3%A9+Crenshaw%2E+1989%2E+Demarginalizing+the+intersection+of+race+and+sex%3A+A+black+feminist+critique+of+antidiscrimination+doctrine%2C+feminist+theory+and+antiracist+politics%2E+University+of+Chicago+Lega)
8. Longxu Dou, Qian Liu, Fan Zhou, Changyu Chen, Zili Wang, et al. 2025. Sailor2: Sailing in south-east Asia with inclusive multilingual LLMs. [find](https://scholar.google.com/scholar?q=Longxu+Dou%2C+Qian+Liu%2C+Fan+Zhou%2C+Changyu+Chen%2C+Zili+Wang%2C+et+al%2E+2025%2E+Sailor2%3A+Sailing+in+south%2Deast+Asia+with+inclusive+multilingual+LLMs%2E)
9. David Esiobu, Xiaoqing Tan, Saghar Hosseini, Megan Ung, Yuchen Zhang, et al. 2023. ROBBIE: Robust bias evaluation of large generative language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3764–3814, Singapore. Association for Computational… [find](https://scholar.google.com/scholar?q=David+Esiobu%2C+Xiaoqing+Tan%2C+Saghar+Hosseini%2C+Megan+Ung%2C+Yuchen+Zhang%2C+et+al%2E+2023%2E+ROBBIE%3A+Robust+bias+evaluation+of+large+generative+language+models%2E+In+Proceedings+of+the+2023+Conference+on+Empirica)
10. Mahammed Kamruzzaman, Md. Shovon, and Gene Kim. 2024. Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models. In Findings of the Association for Computational Linguistics ACL 2024, pages 8940–8965, Bangkok, Thailand and virtual meeting. Associa… [find](https://scholar.google.com/scholar?q=Mahammed+Kamruzzaman%2C+Md%2E+Shovon%2C+and+Gene+Kim%2E+2024%2E+Investigating+Subtler+Biases+in+LLMs%3A+Ageism%2C+Beauty%2C+Institutional%2C+and+Nationality+Bias+in+Generative+Models%2E+In+Findings+of+the+Association+for)
11. Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xin Zhou, Enzhi Wang, and Xiaohang Dong. 2024. [Better Zero-Shot Reasoning with Role-Play Prompting](https://md.research.elamur.ai/free/en/papers/kong-2023-better-zero-shot-reasoning-role/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language…
12. Louis Kwok, Michal Bravansky, and Lewis Griffin. 2024. Evaluating cultural adaptability of a large language model via simulation of synthetic personas. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Louis+Kwok%2C+Michal+Bravansky%2C+and+Lewis+Griffin%2E+2024%2E+Evaluating+cultural+adaptability+of+a+large+language+model+via+simulation+of+synthetic+personas%2E+In+First+Conference+on+Language+Modeling%2E)
13. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with PagedAttention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/).
14. Ang Li, Haozhe Chen, Hongseok Namkoong, and Tianyi Peng. 2025. LLM generated persona is a promise with a catch. [find](https://scholar.google.com/scholar?q=Ang+Li%2C+Haozhe+Chen%2C+Hongseok+Namkoong%2C+and+Tianyi+Peng%2E+2025%2E+LLM+generated+persona+is+a+promise+with+a+catch%2E)
15. Bryan Li, Samar Haider, and Chris Callison-Burch. 2024a. This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models. [find](https://scholar.google.com/scholar?q=Bryan+Li%2C+Samar+Haider%2C+and+Chris+Callison%2DBurch%2E+2024a%2E+This+Land+is+%7BYour%2C+My%7D+Land%3A+Evaluating+Geopolitical+Biases+in+Language+Models%2E)
16. Cheng Li, Mengzhuo Chen, Jindong Wang, Sunayana Sitaram, and Xing Xie. 2024b. [CultureLLM: Incorporating cultural differences into large language models](https://md.research.elamur.ai/free/en/papers/li-2024-culturellm-incorporating-cultural-differences-large/). In Advances in Neural Information Processing Systems, volume 37, pages 84799–84838. Curran Associates, Inc.
17. Cheng Li, Damien Teney, Linyi Yang, Qingsong Wen, Xing Xie, and Jindong Wang. 2024c. [CulturePark: Boosting cross-cultural understanding in large language models](https://md.research.elamur.ai/free/en/papers/li-2024-culturepark-boosting-cross-cultural-understanding/). In Advances in Neural Information Processing Systems, volume 37, pages 65183–65216. Curran Associates, Inc.
18. Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, and Tong Zhang. 2024. [Mitigating the alignment tax of RLHF](https://md.research.elamur.ai/free/en/papers/lin-2024-mitigating-alignment-tax-rlhf/). In Proceedings of the 2024 Conference on Empirical Me…
19. Qwen, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, et al. 2025. Qwen2.5 technical report. [find](https://scholar.google.com/scholar?q=Qwen%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+et+al%2E+2025%2E+Qwen2%2E5+technical+report%2E)
20. Reem Masoud, Ziquan Liu, Martin Ferianc, Philip C. Treleaven, and Miguel Rodrigues Rodrigues. 2025. [Cultural alignment in large language models: An explanatory analysis based on hofstede’s cultural dimensions](https://md.research.elamur.ai/free/en/papers/masoud-2025-cultural-alignment-large-language-models/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 84…
21. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2023. [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/).
22. MetaAI. 2024a. Introducing Llama 3.1: Our most capable models to date. [https://ai.meta.com/blog/meta-llama-3-1/](https://ai.meta.com/blog/meta-llama-3-1/). [↗](https://ai.meta.com/blog/meta-llama-3-1/)
23. MetaAI. 2024b. Llama 3.2: Revolutionizing edge AI and vision with open, customizable models. [https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/). [↗](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/)
24. Microsoft, Abdelrahman Abouelenin, Atabak Ashfaq, Adam Atkinson, Hany Awadalla, Nguyen Bach, et al. 2025. [Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-LoRAs](https://md.research.elamur.ai/free/en/papers/microsoft-2025-phi-4-mini-technical-report/).
25. William Miner. 2023. In Singapore, religious diversity and tolerance go hand in hand. [find](https://scholar.google.com/scholar?q=William+Miner%2E+2023%2E+In+Singapore%2C+religious+diversity+and+tolerance+go+hand+in+hand%2E)
26. MistralAI. 2025. Mistral small 3.1 \| mistral AI. [https://mistral.ai/news/mistral-small-3-1](https://mistral.ai/news/mistral-small-3-1). [↗](https://mistral.ai/news/mistral-small-3-1)
27. Mohammad Alami Musa. 2023. Singapore’s secularism and its pragmatic approach to religion. Religions, 14(2):219. [find](https://scholar.google.com/scholar?q=Mohammad+Alami+Musa%2E+2023%2E+Singapore%E2%80%99s+secularism+and+its+pragmatic+approach+to+religion%2E+Religions%2C+14%282%29%3A219%2E)
28. Junho Myung, Nayeon Lee, Yi Zhou, Jiho Jin, Rifki Afina Putri, et al. 2024. [BLEnD: A benchmark for llms on everyday knowledge in diverse cultures and languages](https://md.research.elamur.ai/free/en/papers/myung-2024-blend-benchmark-llms-everyday-knowledge/). In Advances in Neural Information Processing Systems, volume 37, pages 78104–78146. Curran Associates, Inc.
29. Raymond Ng, Thanh Ngan Nguyen, Yuli Huang, Ngee Chia Tai, Wai Yi Leong, Wei Qi Leong, et al. 2025. [SEA-LION: Southeast asian languages in one network](https://md.research.elamur.ai/free/en/papers/ng-2025-sea-lion-southeast-asian-languages/).
30. Justin Ong. 2023. Singaporean youth less likely than older generations to have seen their social status rise: IPS study. [https://www.todayonline.com/singapore/youth-social-status-ips-study-2089046](https://www.todayonline.com/singapore/youth-social-status-ips-study-2089046). [↗](https://www.todayonline.com/singapore/youth-social-status-ips-study-2089046)
31. OpenAI. 2024a. Hello [https://openai.com/index/hello-gpt-4o/](https://openai.com/index/hello-gpt-4o/). [↗](https://openai.com/index/hello-gpt-4o/)
32. OpenAI. 2024b. Introducing GPT-4.1 in the API. [https://openai.com/index/gpt-4-1/](https://openai.com/index/gpt-4-1/). [↗](https://openai.com/index/gpt-4-1/)
33. Giada Pistilli, Alina Leidinger, Yacine Jernite, Atoosa Kasirzadeh, Alexandra Sasha Luccioni, and Margaret Mitchell. 2024. CIVICS: Building a dataset for examining culturally-informed values in large language models. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 7(1):1132–1144. [find](https://scholar.google.com/scholar?q=Giada+Pistilli%2C+Alina+Leidinger%2C+Yacine+Jernite%2C+Atoosa+Kasirzadeh%2C+Alexandra+Sasha+Luccioni%2C+and+Margaret+Mitchell%2E+2024%2E+CIVICS%3A+Building+a+dataset+for+examining+culturally%2Dinformed+values+in+large+)
34. Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto. 2023. [Whose opinions do language models reflect?](https://md.research.elamur.ai/free/en/papers/santurkar-2023-whose-opinions-language-models-reflect/) In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 29971–30004. PMLR.
35. Murray Shanahan, Kyle McDonell, and Laria Reynolds. 2023. [Role-play with large language models](https://md.research.elamur.ai/free/en/papers/shanahan-2023-role-play-large-language-models/).
36. Taylor Sorensen, Liwei Jiang, Jena D. Hwang, Sydney Levine, Valentina Pyatkin, et al. 2024. [Value kaleidoscope: Engaging AI with pluralistic human values, rights, and duties](https://md.research.elamur.ai/free/en/papers/sorensen-2023-value-kaleidoscope-engaging-ai-pluralistic/). Proceedings of the AAAI Conference on Artificial Intelligence, 38(18):19937–19947.
37. Nicholas Sukiennik, Chen Gao, Fengli Xu, and Yong Li. 2025. An evaluation of cultural value alignment in LLM. [find](https://scholar.google.com/scholar?q=Nicholas+Sukiennik%2C+Chen+Gao%2C+Fengli+Xu%2C+and+Yong+Li%2E+2025%2E+An+evaluation+of+cultural+value+alignment+in+LLM%2E)
38. Bryan Chen Zhengyu Tan, Shaun Khoo, Bich Ngoc Doan, Zhengyuan Liu, Nancy F. Chen, and Roy Ka-Wei Lee. 2026a. Small changes, big impact: Demographic bias in LLM-based hiring through subtle sociocultural markers in anonymised resumes. [find](https://scholar.google.com/scholar?q=Bryan+Chen+Zhengyu+Tan%2C+Shaun+Khoo%2C+Bich+Ngoc+Doan%2C+Zhengyuan+Liu%2C+Nancy+F%2E+Chen%2C+and+Roy+Ka%2DWei+Lee%2E+2026a%2E+Small+changes%2C+big+impact%3A+Demographic+bias+in+LLM%2Dbased+hiring+through+subtle+sociocultura)
39. Bryan Chen Zhengyu Tan and Roy Ka-Wei Lee. 2025. Unmasking implicit bias: Evaluating persona-prompted LLM responses in power-disparate social scenarios. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Techn… [find](https://scholar.google.com/scholar?q=Bryan+Chen+Zhengyu+Tan+and+Roy+Ka%2DWei+Lee%2E+2025%2E+Unmasking+implicit+bias%3A+Evaluating+persona%2Dprompted+LLM+responses+in+power%2Ddisparate+social+scenarios%2E+In+Proceedings+of+the+2025+Conference+of+the+Na)
40. Bryan Chen Zhengyu Tan, Weihua Zheng, Zhengyuan Liu, Nancy F. Chen, Hwaran Lee, Kenny Tsu Wei Choo, and Roy Ka-Wei Lee. 2026b. [BLEnD-vis: Benchmarking multimodal cultural understanding in vision language models](https://md.research.elamur.ai/free/en/papers/tan-2026-blend-vis-benchmarking-multimodal-cultural/). In Proceedings of the 19th Conference of the European Chapter of the Association for Com…
41. Yan Tao, Olga Viberg, Ryan S Baker, and René F Kizilcec. 2024. [Cultural bias and cultural alignment of large language models](https://md.research.elamur.ai/free/en/papers/tao-2023-cultural-bias-cultural-alignment-large/). PNAS Nexus, 3(9):pgae346.
42. Maxim Tkachenko, Mikhail Malyuk, Andrey Holmanyuk, and Nikolai Liubimov. 2020-2022. Label Studio: Data labeling software. Open source software available from [https://github.com/heartexlabs/label-studio](https://github.com/heartexlabs/label-studio). [↗](https://github.com/heartexlabs/label-studio)
43. Kush R. Varshney. 2024. Decolonial AI alignment: Openness, visesa-dharma, and including excluded knowledges. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 7(1):1467–1481. [find](https://scholar.google.com/scholar?q=Kush+R%2E+Varshney%2E+2024%2E+Decolonial+AI+alignment%3A+Openness%2C+visesa%2Ddharma%2C+and+including+excluded+knowledges%2E+Proceedings+of+the+AAAI%2FACM+Conference+on+AI%2C+Ethics%2C+and+Society%2C+7%281%29%3A1467%E2%80%931481%2E)
44. Yuhang Wang, Yanxu Zhu, Chao Kong, Shuyu Wei, Xiaoyuan Yi, Xing Xie, and Jitao Sang. 2024a. CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models. In Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLP, pages 1–16, Bangkok, Thailand. Association for C… [find](https://scholar.google.com/scholar?q=Yuhang+Wang%2C+Yanxu+Zhu%2C+Chao+Kong%2C+Shuyu+Wei%2C+Xiaoyuan+Yi%2C+Xing+Xie%2C+and+Jitao+Sang%2E+2024a%2E+CDEval%3A+A+Benchmark+for+Measuring+the+Cultural+Dimensions+of+Large+Language+Models%2E+In+Proceedings+of+the+2n)
45. Zekun Moore Wang, Zhongyuan Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Stephen W. Huang, Jie Fu, and Junran Peng. 2024b. [RoleLLM: Benchmarking, eliciting, and enhancing role-playing abil…](https://md.research.elamur.ai/free/en/papers/wang-2023-rolellm-benchmarking-eliciting-enhancing-role/)
46. Ping Wu, Guobin Shen, Dongcheng Zhao, Yuwei Wang, Yiting Dong, Yu Shi, Enmeng Lu, Feifei Zhao, and Yi Zeng. 2025. CVC: A large-scale chinese value rule corpus for value alignment of large language models. [find](https://scholar.google.com/scholar?q=Ping+Wu%2C+Guobin+Shen%2C+Dongcheng+Zhao%2C+Yuwei+Wang%2C+Yiting+Dong%2C+Yu+Shi%2C+Enmeng+Lu%2C+Feifei+Zhao%2C+and+Yi+Zeng%2E+2025%2E+CVC%3A+A+large%2Dscale+chinese+value+rule+corpus+for+value+alignment+of+large+language+mod)
47. Wenxuan Zhang, Hou Pong Chan, Yiran Zhao, Mahani Aljunied, Jianyu Wang, Chaoqun Liu, Yue Deng, Zhiqiang Hu, Weiwen Xu, Yew Ken Chia, Xin Li, and Lidong Bing. 2025. SeaLLMs 3: Open foundation and chat multilingual large language models for southeast asian languages. In Proceedings of the 2025 Confere… [find](https://scholar.google.com/scholar?q=Wenxuan+Zhang%2C+Hou+Pong+Chan%2C+Yiran+Zhao%2C+Mahani+Aljunied%2C+Jianyu+Wang%2C+Chaoqun+Liu%2C+Yue+Deng%2C+Zhiqiang+Hu%2C+Weiwen+Xu%2C+Yew+Ken+Chia%2C+Xin+Li%2C+and+Lidong+Bing%2E+2025%2E+SeaLLMs+3%3A+Open+foundation+and+chat+)
48. Wenlong Zhao, Debanjan Mondal, Niket Tandon, Danica Dillion, Kurt Gray, and Yuling Gu. 2024. World-ValuesBench: A large-scale benchmark dataset for multi-cultural value awareness of language models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Reso… [find](https://scholar.google.com/scholar?q=Wenlong+Zhao%2C+Debanjan+Mondal%2C+Niket+Tandon%2C+Danica+Dillion%2C+Kurt+Gray%2C+and+Yuling+Gu%2E+2024%2E+World%2DValuesBench%3A+A+large%2Dscale+benchmark+dataset+for+multi%2Dcultural+value+awareness+of+language+models%2E+I)

*Updated 2 November 2026*