---
title: "A Game-Theoretic Negotiation Framework for Cross-Cultural"
description: "Large language models lean toward WEIRD (Western, Educated, Industrialized, Rich, Democratic) values. 52 references."
authors: ["Guoxi Zhang", "Jiawei Chen", "Tianzhuo Yang", "Jiaming Ji", "Yaodong Yang", "Juntao Dai"]
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.49/"
doi: "10.18653/v1/2026.acl-long.49"
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/zhang-2026-game-theoretic-negotiation-framework-cross/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-game-theoretic-negotiation-framework-cross/)

[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/20/) / A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus

# A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus

**Authors:** Guoxi Zhang, [Jiawei Chen](https://md.research.elamur.ai/free/en/authors/jiawei-chen/), [Tianzhuo Yang](https://md.research.elamur.ai/free/en/authors/tianzhuo-yang/), [Jiaming Ji](https://md.research.elamur.ai/free/en/authors/jiaming-ji/), [Yaodong Yang](https://md.research.elamur.ai/free/en/authors/yaodong-yang/) and [Juntao Dai](https://md.research.elamur.ai/free/en/authors/juntao-dai/) · **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.49/) · [PDF](https://aclanthology.org/2026.acl-long.49.pdf) · [DOI 10.18653/v1/2026.acl-long.49](https://doi.org/10.18653/v1/2026.acl-long.49) · [OpenAlex](https://openalex.org/W7166881396)

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

## Summary
Large language models lean toward WEIRD (Western, Educated, Industrialized, Rich, Democratic) values. In a pilot on the Inglehart–Welzel map, gpt-oss-20b and LLaMA-3.3-70b approximated U.S. survey positions but merged non-WEIRD societies into one indistinct group. Their two-culture compromises also drifted toward secular, self-expressive positions. The authors draw on Rawls's notion of Overlapping Consensus and treat cross-cultural agreement as a non-cooperative game whose target solution is a Nash Equilibrium.

In their Nash Consensus Negotiation framework, culture-anchored LLMs (built from WVS data and cultural texts) trade weighted natural-language guidelines. Each agent's utility rewards acceptability to the other side and faithfulness to its own initial values, and it penalizes redundant guidelines. Equilibria are computed in restricted subgames while agents keep adding new proposals. Across eight countries, metrics and human studies show more balanced, higher-quality consensus and less WEIRD assimilation than debate- or voting-style baselines.

Negotiation outputs were then reused for fine-tuning, which cut cultural distances by up to 95.53%. This gives a principled route to culturally fairer models.

## Key points
- Utility per guideline set: Acceptance + λ·Consistency − γ·Redundancy, using embedding similarity to other agents' guidelines and to the agent's initial guidelines G₀.
- Fine-tuning used preference optimization and supervised reasoning on negotiation data across several LLM architectures, reducing cultural distance by up to 95.53%.
- Evaluation covered eight countries but only seven of the 28 possible culture pairs, due to GPU/API limits. Tests included bilateral and trilateral (Appendix H.3) negotiations; settings with more than three parties are untested.
- Efficiency: negotiations usually converge in 2–3 rounds. The NE solver takes under 0.1% of wall-clock time; in the three-agent setup, each LLaMA-3.3 runs on 8×80 GB A100s.
- The dataset was built by 31 professional annotators, and the data and training code are released. A noted limitation is that WVS lacks the newest survey waves.

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

📚 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 · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 626 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 249 works · [🎯 Management Science and Operations Research](https://md.research.elamur.ai/free/en/shelves/decision-sciences/management-science-and-operations-research/) · 134 works

## Cite

Cite as: Guoxi Zhang, Jiawei Chen, Tianzhuo Yang, Jiaming Ji, Yaodong Yang and Juntao Dai. 2026. A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus. 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{zhang2026game,
  title = {{A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus}},
  author = {Guoxi Zhang, Jiawei Chen, Tianzhuo Yang, Jiaming Ji, Yaodong Yang and Juntao Dai},
  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.49},
  url = {https://doi.org/10.18653/v1/2026.acl-long.49}
}
```

- [← previous A Fusion-Aware Two-Stage Framework for Mispronunciation Detection and Diagnosis in Low-Resource Modern Standard Arabic](https://md.research.elamur.ai/free/en/papers/yang-2026-fusion-aware-two-stage-framework/)
- [next → A Generative Grammar Underlying the Voynich Manuscript, the Pastiche Hypothesis: Evidence from Large Language Models](https://md.research.elamur.ai/free/en/papers/turenne-2026-generative-grammar-underlying-voynich-manuscript/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/)

## References

52 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Goshi Aoki. 2024. Large language models in politics and democracy: A comprehensive survey. Preprint, arXiv:2412.04498. — [arXiv:2412.04498](https://arxiv.org/abs/2412.04498) [find](https://scholar.google.com/scholar?q=Goshi+Aoki%2E+2024%2E+Large+language+models+in+politics+and+democracy%3A+A+comprehensive+survey%2E+Preprint%2C+arXiv%3A2412%2E04498%2E+%E2%80%94+%5BarXiv%3A2412%2E04498%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2412%2E04498%29)
2. Noam Benkler, Drisana Mosaphir, Scott Friedman, Andrew Smart, and Sonja Schmer-Galunder. 2023. Assessing LLMs for moral value pluralism. Preprint, arXiv:2312.10075. — [arXiv:2312.10075](https://arxiv.org/abs/2312.10075) [find](https://scholar.google.com/scholar?q=Noam+Benkler%2C+Drisana+Mosaphir%2C+Scott+Friedman%2C+Andrew+Smart%2C+and+Sonja+Schmer%2DGalunder%2E+2023%2E+Assessing+LLMs+for+moral+value+pluralism%2E+Preprint%2C+arXiv%3A2312%2E10075%2E+%E2%80%94+%5BarXiv%3A2312%2E10075%5D%28https%3A%2F%2Farxiv%2E)
3. Shaily Bhatt and Fernando Diaz. 2024. Extrinsic evaluation of cultural competence in large language models. arXiv preprint arXiv:2406.11565. [find](https://scholar.google.com/scholar?q=Shaily+Bhatt+and+Fernando+Diaz%2E+2024%2E+Extrinsic+evaluation+of+cultural+competence+in+large+language+models%2E+arXiv+preprint+arXiv%3A2406%2E11565%2E)
4. Nathan Brugnone, Noam Benkler, Peter Revay, and Rebecca Myhre. 2024. Is from ought? A comparison of unsupervised methods for structuring values-based wisdom-of-crowds estimates. Researchgate. [find](https://scholar.google.com/scholar?q=Nathan+Brugnone%2C+Noam+Benkler%2C+Peter+Revay%2C+and+Rebecca+Myhre%2E+2024%2E+Is+from+ought%3F+A+comparison+of+unsupervised+methods+for+structuring+values%2Dbased+wisdom%2Dof%2Dcrowds+estimates%2E+Researchgate%2E)
5. Samuel Cahyawijaya. 2024. Llm for everyone: Representing the underrepresented in large language models. Hong Kong University of Science and Technology (Hong Kong). [find](https://scholar.google.com/scholar?q=Samuel+Cahyawijaya%2E+2024%2E+Llm+for+everyone%3A+Representing+the+underrepresented+in+large+language+models%2E+Hong+Kong+University+of+Science+and+Technology+%28Hong+Kong%29%2E)
6. Pew Research Center. global attitudes survey 2014. [find](https://scholar.google.com/scholar?q=Pew+Research+Center%2E+global+attitudes+survey+2014%2E)
7. Pew research [https://www.selectdataset.com/dataset/](https://www.selectdataset.com/dataset/) 1be490648bfe3bd6a0b2fd4bc60deff5. cessed: 2024-10-27. [↗](https://www.selectdataset.com/dataset/)
8. Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, and Jinchao Xu. 2024. [AceGPT, Localizing Large Language Models in Arabic](https://md.research.elamur.ai/free/en/papers/huang-2024-acegpt-localizing-large-language-models/). Preprint, arXiv:2309.12053.
9. Ac-Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan Liu. 2023. [ChatEval: Towards better LLM-based evaluators through multi-agent debate](https://md.research.elamur.ai/free/en/papers/chan-2023-chateval-better-llm-based/). Preprint, arXiv:2308.07201.
10. Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin, Chan Young Park, Shuyue Stella Li, Sahithya Ravi, Mehar Bhatia, Maria Antoniak, Yulia Tsvetkov, Vered Shwartz, and Yejin Choi. 2024. Culturalbench: a robust, diverse and challenging benchmark on measuring the (lack of) cultural knowledge of llms. Preprint,… — [arXiv:2410.02677](https://arxiv.org/abs/2410.02677) [find](https://scholar.google.com/scholar?q=Yu+Ying+Chiu%2C+Liwei+Jiang%2C+Bill+Yuchen+Lin%2C+Chan+Young+Park%2C+Shuyue+Stella+Li%2C+Sahithya+Ravi%2C+Mehar+Bhatia%2C+Maria+Antoniak%2C+Yulia+Tsvetkov%2C+Vered+Shwartz%2C+and+Yejin+Choi%2E+2024%2E+Culturalbench%3A+a+robust)
11. Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. 2023. [Improving factuality and reasoning in language models through multiagent debate](https://md.research.elamur.ai/free/en/papers/du-2023-improving-factuality-reasoning-language-models/). Preprint, arXiv:2305.14325.
12. Miroslav Dudík and Geoffrey J. Gordon. 2013. A game-theoretic approach to modeling cross-cultural negotiation. In Katia Sycara, Michele Gelfand, and Allison Abbe, editors, Models for Intercultural Collaboration and Negotiation, pages 157–163. Springer Netherlands, Dordrecht. [find](https://scholar.google.com/scholar?q=Miroslav+Dud%C3%ADk+and+Geoffrey+J%2E+Gordon%2E+2013%2E+A+game%2Dtheoretic+approach+to+modeling+cross%2Dcultural+negotiation%2E+In+Katia+Sycara%2C+Michele+Gelfand%2C+and+Allison+Abbe%2C+editors%2C+Models+for+Intercultural+Col)
13. Esin Durmus, Karina Nguyen, Thomas I. Liao, Nicholas Schiefer, Amanda Askell, Anton Bakhtin, Carol Chen, Zac Hatfield-Dodds, Danny Hernandez, Nicholas Joseph, Liane Lovitt, Sam McCandlish, Orowa Sikder, Alex Tamkin, Janel Thamkul, Jared Kaplan, Jack Clark, and Deep Ganguli. 2024. [Towards measuring t…](https://md.research.elamur.ai/free/en/papers/durmus-2023-towards-measuring-representation-subjective-global/)
14. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — [The Llama 3 Herd of Models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/)
15. C. Haerpfer, R. Inglehart, A. Moreno, C. Welzel, K. Kizilova, J. Diez-Medrano, M. Lagos, P. Norris, E. Ponarin, and B. Puranen. 2020. World values survey: Round seven – country-pooled datafile. Madrid, Spain & Vienna, Austria: JD Systems Institute & WVSA Secretariat. [find](https://scholar.google.com/scholar?q=C%2E+Haerpfer%2C+R%2E+Inglehart%2C+A%2E+Moreno%2C+C%2E+Welzel%2C+K%2E+Kizilova%2C+J%2E+Diez%2DMedrano%2C+M%2E+Lagos%2C+P%2E+Norris%2C+E%2E+Ponarin%2C+and+B%2E+Puranen%2E+2020%2E+World+values+survey%3A+Round+seven+%E2%80%93+country%2Dpooled+datafile%2E+Madrid)
16. Wenyue Hua, Ollie Liu, Lingyao Li, Alfonso Amayuelas, Julie Chen, Lucas Jiang, Mingyu Jin, Lizhou Fan, Fei Sun, William Wang, Xintong Wang, and Yongfeng Zhang. 2024. Game-theoretic llm: Agent workflow for negotiation games. Preprint, arXiv:2411.05990. — [arXiv:2411.05990](https://arxiv.org/abs/2411.05990) [find](https://scholar.google.com/scholar?q=Wenyue+Hua%2C+Ollie+Liu%2C+Lingyao+Li%2C+Alfonso+Amayuelas%2C+Julie+Chen%2C+Lucas+Jiang%2C+Mingyu+Jin%2C+Lizhou+Fan%2C+Fei+Sun%2C+William+Wang%2C+Xintong+Wang%2C+and+Yongfeng+Zhang%2E+2024%2E+Game%2Dtheoretic+llm%3A+Agent+workflow)
17. Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Dingjie Song, Zhihong Chen, Abdulmohsen Alharthi, Bang An, Juncai He, Ziche Liu, Zhiyi Zhang, Junying Chen, Jianquan Li, Benyou Athul Paul Jacob, Yikang Shen, Gabriele Farina, and Jacob Andreas. 2023. The consensus game: Language model gener… — [arXiv:2310.09139](https://arxiv.org/abs/2310.09139) [find](https://scholar.google.com/scholar?q=Huang+Huang%2C+Fei+Yu%2C+Jianqing+Zhu%2C+Xuening+Sun%2C+Hao+Cheng%2C+Dingjie+Song%2C+Zhihong+Chen%2C+Abdulmohsen+Alharthi%2C+Bang+An%2C+Juncai+He%2C+Ziche+Liu%2C+Zhiyi+Zhang%2C+Junying+Chen%2C+Jianquan+Li%2C+Benyou+Athul+Paul+Ja)
18. Zhibin Jiang. 2025. Editorial: Large language models drive social evolution and governance innovations. Digital Transformation and Society, 4(1):1–4. [find](https://scholar.google.com/scholar?q=Zhibin+Jiang%2E+2025%2E+Editorial%3A+Large+language+models+drive+social+evolution+and+governance+innovations%2E+Digital+Transformation+and+Society%2C+4%281%29%3A1%E2%80%934%2E)
19. Mohsinul Kabir, Ajwad Abrar, and Sophia Ananiadou. 2025. Break the checkbox: Challenging closed-style evaluations of cultural alignment in llms. Preprint, arXiv:2502.08045. [find](https://scholar.google.com/scholar?q=Mohsinul+Kabir%2C+Ajwad+Abrar%2C+and+Sophia+Ananiadou%2E+2025%2E+Break+the+checkbox%3A+Challenging+closed%2Dstyle+evaluations+of+cultural+alignment+in+llms%2E+Preprint%2C+arXiv%3A2502%2E08045%2E)
20. Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle, Terry Ruas, and Bela Gipp. 2025. Voting or consensus? decision-making in multi-agent debate. In Findings of the Association for Computational Linguistics: ACL 2025, page 11640–11671. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Lars+Benedikt+Kaesberg%2C+Jonas+Becker%2C+Jan+Philip+Wahle%2C+Terry+Ruas%2C+and+Bela+Gipp%2E+2025%2E+Voting+or+consensus%3F+decision%2Dmaking+in+multi%2Dagent+debate%2E+In+Findings+of+the+Association+for+Computational+Li)
21. Akbir Khan, John Hughes, Dan Valentine, Laura Ruis, Kshitij Sachan, Ansh Radhakrishnan, Edward Grefenstette, Samuel R. Bowman, Tim Rocktäschel, and Ethan Perez. 2024. [Debating with more persuasive LLMs leads to more truthful answers](https://md.research.elamur.ai/free/en/papers/khan-2024-debating-more-persuasive-llms-leads/). Preprint, arXiv:2402.06782.
22. Julia Kharchenko, Tanya Roosta, Aman Chadha, and Chirag Shah. 2024. How well do llms represent values across cultures? empirical analysis of llm responses based on hofstede cultural dimensions. Preprint, arXiv:2406.14805. — [arXiv:2406.14805](https://arxiv.org/abs/2406.14805) [find](https://scholar.google.com/scholar?q=Julia+Kharchenko%2C+Tanya+Roosta%2C+Aman+Chadha%2C+and+Chirag+Shah%2E+2024%2E+How+well+do+llms+represent+values+across+cultures%3F+empirical+analysis+of+llm+responses+based+on+hofstede+cultural+dimensions%2E+Prepri)
23. Marc Lanctot, Vinicius Zambaldi, Audrunas Gruslys, Angeliki Lazaridou, Karl Tuyls, Julien Perolat, David Silver, and Thore Graepel. 2017. A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning. Preprint, arXiv:1711.00832. — [arXiv:1711.00832](https://arxiv.org/abs/1711.00832) [find](https://scholar.google.com/scholar?q=Marc+Lanctot%2C+Vinicius+Zambaldi%2C+Audrunas+Gruslys%2C+Angeliki+Lazaridou%2C+Karl+Tuyls%2C+Julien+Perolat%2C+David+Silver%2C+and+Thore+Graepel%2E+2017%2E+A+Unified+Game%2DTheoretic+Approach+to+Multiagent+Reinforcement+)
24. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2024. [Encouraging divergent thinking in large language models through multi-agent debate](https://md.research.elamur.ai/free/en/papers/liang-2023-encouraging-divergent-thinking-large-language/). Preprint, arXiv:2305.19118.
25. Yen-Ting Lin and Yun-Nung Chen. 2023. Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model. Preprint, arXiv:2311.17487. — [arXiv:2311.17487](https://arxiv.org/abs/2311.17487) [find](https://scholar.google.com/scholar?q=Yen%2DTing+Lin+and+Yun%2DNung+Chen%2E+2023%2E+Taiwan+LLM%3A+Bridging+the+Linguistic+Divide+with+a+Culturally+Aligned+Language+Model%2E+Preprint%2C+arXiv%3A2311%2E17487%2E+%E2%80%94+%5BarXiv%3A2311%2E17487%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2311%2E1)
26. Xiangyu Liu, Hangtian Jia, Ying Wen, Yujing Hu, Yingfeng Chen, Changjie Fan, Zhipeng Hu, and Yaodong Yang. 2021. Towards unifying behavioral and response diversity for open-ended learning in zero-sum games. In Advances in Neural Information Processing Systems, volume 34, pages 941–952. Curran Associ… [find](https://scholar.google.com/scholar?q=Xiangyu+Liu%2C+Hangtian+Jia%2C+Ying+Wen%2C+Yujing+Hu%2C+Yingfeng+Chen%2C+Changjie+Fan%2C+Zhipeng+Hu%2C+and+Yaodong+Yang%2E+2021%2E+Towards+unifying+behavioral+and+response+diversity+for+open%2Dended+learning+in+zero%2Dsum+)
27. Zhaoming Liu. 2024. Cultural bias in large language models: A comprehensive analysis and mitigation strategies. Journal of Transcultural Communication. [find](https://scholar.google.com/scholar?q=Zhaoming+Liu%2E+2024%2E+Cultural+bias+in+large+language+models%3A+A+comprehensive+analysis+and+mitigation+strategies%2E+Journal+of+Transcultural+Communication%2E)
28. Quan Mai, Susan Gauch, Douglas Adams, and Miaoqing Huang. 2025. Sequence graph network for online debate analysis. Preprint, arXiv:2406.18696. — [arXiv:2406.18696](https://arxiv.org/abs/2406.18696) [find](https://scholar.google.com/scholar?q=Quan+Mai%2C+Susan+Gauch%2C+Douglas+Adams%2C+and+Miaoqing+Huang%2E+2025%2E+Sequence+graph+network+for+online+debate+analysis%2E+Preprint%2C+arXiv%3A2406%2E18696%2E+%E2%80%94+%5BarXiv%3A2406%2E18696%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2406%2E18696%29)
29. Reem I. Masoud, Martin Ferianc, Philip Treleaven, and Miguel Rodrigues. 2025. Cultural alignment in large language models using soft prompt tuning. Preprint, arXiv:2503.16094. — [arXiv:2503.16094](https://arxiv.org/abs/2503.16094) [find](https://scholar.google.com/scholar?q=Reem+I%2E+Masoud%2C+Martin+Ferianc%2C+Philip+Treleaven%2C+and+Miguel+Rodrigues%2E+2025%2E+Cultural+alignment+in+large+language+models+using+soft+prompt+tuning%2E+Preprint%2C+arXiv%3A2503%2E16094%2E+%E2%80%94+%5BarXiv%3A2503%2E16094%5D%28htt)
30. Reem I. Masoud, Ziquan Liu, Martin Ferianc, Philip Treleaven, and Miguel Rodrigues. 2024. [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/). Preprint, arXiv:2309.12342.
31. Yu Meng, Mengzhou Xia, and Danqi Chen. 2024. Simpo: Simple preference optimization with a reference-free reward. Preprint, arXiv:2405.14734. [find](https://scholar.google.com/scholar?q=Yu+Meng%2C+Mengzhou+Xia%2C+and+Danqi+Chen%2E+2024%2E+Simpo%3A+Simple+preference+optimization+with+a+reference%2Dfree+reward%2E+Preprint%2C+arXiv%3A2405%2E14734%2E)
32. Zabir Al Nazi and Wei Peng. 2024. Large language models in healthcare and medical domain: A review. Preprint, arXiv:2401.06775. — [arXiv:2401.06775](https://arxiv.org/abs/2401.06775) [find](https://scholar.google.com/scholar?q=Zabir+Al+Nazi+and+Wei+Peng%2E+2024%2E+Large+language+models+in+healthcare+and+medical+domain%3A+A+review%2E+Preprint%2C+arXiv%3A2401%2E06775%2E+%E2%80%94+%5BarXiv%3A2401%2E06775%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2401%2E06775%29)
33. OpenAI, Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K. Arora, Yu Bai, Bowen Baker, Haiming Bao, Boaz Barak, Ally Bennett, Tyler Bertao, Nivedita Brett, Eugene Brevdo, Greg Brockman, Sebastien Bubeck, Che Chang, and 107 others. 2025. [gpt-oss-120b & gpt-oss-2…](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/)
34. Xianghe Pang, Shuo Tang, Rui Ye, Yuxin Xiong, Bolun Zhang, Yanfeng Wang, and Siheng Chen. 2024. Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation. Preprint, arXiv:2402.05699. — [arXiv:2402.05699](https://arxiv.org/abs/2402.05699) [find](https://scholar.google.com/scholar?q=Xianghe+Pang%2C+Shuo+Tang%2C+Rui+Ye%2C+Yuxin+Xiong%2C+Bolun+Zhang%2C+Yanfeng+Wang%2C+and+Siheng+Chen%2E+2024%2E+Self%2DAlignment+of+Large+Language+Models+via+Monopolylogue%2Dbased+Social+Scene+Simulation%2E+Preprint%2C+arXiv)
35. Tianyi Qiu, Yang Zhang, Xuchuan Huang, Jasmine Xinze Li, Jiaming Ji, and Yaodong Yang. 2024. ProgressGym: Alignment with a millennium of moral progress. Preprint, arXiv:2406.20087. — [arXiv:2406.20087](https://arxiv.org/abs/2406.20087) [find](https://scholar.google.com/scholar?q=Tianyi+Qiu%2C+Yang+Zhang%2C+Xuchuan+Huang%2C+Jasmine+Xinze+Li%2C+Jiaming+Ji%2C+and+Yaodong+Yang%2E+2024%2E+ProgressGym%3A+Alignment+with+a+millennium+of+moral+progress%2E+Preprint%2C+arXiv%3A2406%2E20087%2E+%E2%80%94+%5BarXiv%3A2406%2E20087)
36. Yao Qu and Jue Wang. 2024. Performance and biases of large language models in public opinion simulation. Humanities and Social Sciences Communications, 11(1):1–13. [find](https://scholar.google.com/scholar?q=Yao+Qu+and+Jue+Wang%2E+2024%2E+Performance+and+biases+of+large+language+models+in+public+opinion+simulation%2E+Humanities+and+Social+Sciences+Communications%2C+11%281%29%3A1%E2%80%9313%2E)
37. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2024. [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/). Preprint, arXiv:2305.18290.
38. John Rawls. 1993. Political Liberalism. Columbia University Press. [find](https://scholar.google.com/scholar?q=John+Rawls%2E+1993%2E+Political+Liberalism%2E+Columbia+University+Press%2E)
39. Nils Reimers and Iryna Gurevych. 2019. [Sentence-BERT: Sentence embeddings using siamese BERT-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). Preprint, arXiv:1908.10084.
40. Shalom H. Schwartz. An overview of the schwartz theor of basic values. [https://scholarworks.gvsu.edu/or-pc/vol2/iss1/11/](https://scholarworks.gvsu.edu/or-pc/vol2/iss1/11/). [↗](https://scholarworks.gvsu.edu/or-pc/vol2/iss1/11/)
41. Shalom H. Schwartz. 1992. Universals in the Content and Structure of Values: Theoretical Advances and Empirical Tests in 20 Countries. In Mark P. Zanna, editor, Advances in Experimental Social Psychology, volume 25, pages 1–65. Academic Press. [find](https://scholar.google.com/scholar?q=Shalom+H%2E+Schwartz%2E+1992%2E+Universals+in+the+Content+and+Structure+of+Values%3A+Theoretical+Advances+and+Empirical+Tests+in+20+Countries%2E+In+Mark+P%2E+Zanna%2C+editor%2C+Advances+in+Experimental+Social+Psychol)
42. Statista. 2025. Beijing’s minimum hourly wage. [find](https://scholar.google.com/scholar?q=Statista%2E+2025%2E+Beijing%E2%80%99s+minimum+hourly+wage%2E)
43. Qineng Wang, Zihao Wang, Ying Su, Hanghang Tong, and Yangqiu Song. 2024a. [Rethinking the bounds of LLM reasoning: Are multi-agent discussions the key?](https://md.research.elamur.ai/free/en/papers/wang-2024-rethinking-bounds-llm-reasoning/) Preprint, arXiv:2402.18272.
44. Shen Wang, Tianlong Xu, Hang Li, Chaoli Zhang, Joleen Liang, Jiliang Tang, Philip S. Yu, and Qingsong Wen. 2024b. [Large language models for education: A survey and outlook](https://md.research.elamur.ai/free/en/papers/wang-2024-large-language-models-education-survey/). Preprint, arXiv:2403.18105.
45. Yuhang Wang, Yanxu Zhu, Chao Kong, Shuyu Wei, Xiaoyuan Yi, Xing Xie, and Jitao Sang. 2024c. Cdeval: A benchmark for measuring the cultural dimensions of large language models. Preprint, arXiv:2311.16421. [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+2024c%2E+Cdeval%3A+A+benchmark+for+measuring+the+cultural+dimensions+of+large+language+models%2E+Preprint%2C+arXiv%3A2311%2E164)
46. Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, and Heng Ji. 2024d. [Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration](https://md.research.elamur.ai/free/en/papers/wang-2023-unleashing-emergent-cognitive-synergy-large/). Preprint, arXiv:2307.05300.
47. Jian Yang, D. Zhang, A.F. Frangi, and Jing yu Yang. 2004. Two-dimensional pca: a new approach to appearance-based face representation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(1):131–137. [find](https://scholar.google.com/scholar?q=Jian+Yang%2C+D%2E+Zhang%2C+A%2EF%2E+Frangi%2C+and+Jing+yu+Yang%2E+2004%2E+Two%2Ddimensional+pca%3A+a+new+approach+to+appearance%2Dbased+face+representation+and+recognition%2E+IEEE+Transactions+on+Pattern+Analysis+and+Machine)
48. Joshua C. Yang, Damian Dailisan, Marcin Korecki, Carina I. Hausladen, and Dirk Helbing. 2024. LLM voting: Human choices and AI collective decision making. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 7:1696–1708. [find](https://scholar.google.com/scholar?q=Joshua+C%2E+Yang%2C+Damian+Dailisan%2C+Marcin+Korecki%2C+Carina+I%2E+Hausladen%2C+and+Dirk+Helbing%2E+2024%2E+LLM+voting%3A+Human+choices+and+AI+collective+decision+making%2E+Proceedings+of+the+AAAI%2FACM+Conference+on+AI%2C)
49. Jing Yao, Xiaoyuan Yi, Xiting Wang, Yifan Gong, and Xing Xie. 2023. Value fulcra: Mapping large language models to the multidimensional spectrum of basic human values. Preprint, arXiv:2311.10766. — [arXiv:2311.10766](https://arxiv.org/abs/2311.10766) [find](https://scholar.google.com/scholar?q=Jing+Yao%2C+Xiaoyuan+Yi%2C+Xiting+Wang%2C+Yifan+Gong%2C+and+Xing+Xie%2E+2023%2E+Value+fulcra%3A+Mapping+large+language+models+to+the+multidimensional+spectrum+of+basic+human+values%2E+Preprint%2C+arXiv%3A2311%2E10766%2E+%E2%80%94+%5Ba)
50. Baofeng Zhang, Debao Chang, Zhanjie Li, and Dan Ma. 2017. On convergence rate for multi-agent consensus: A community detection algorithm. In 2017 32nd Youth Academic Annual Conference of Chinese Association of Automation (YAC), pages 72–77. [find](https://scholar.google.com/scholar?q=Baofeng+Zhang%2C+Debao+Chang%2C+Zhanjie+Li%2C+and+Dan+Ma%2E+2017%2E+On+convergence+rate+for+multi%2Dagent+consensus%3A+A+community+detection+algorithm%2E+In+2017+32nd+Youth+Academic+Annual+Conference+of+Chinese+Assoc)
51. Hangfan Zhang, Zhiyao Cui, Xinrun Wang, Qiaosheng Zhang, Zhen Wang, Dinghao Wu, and Shuyue Hu. 2025. If multi-agent debate is the answer, what is the question? Preprint, arXiv:2502.08788. — [arXiv:2502.08788](https://arxiv.org/abs/2502.08788) [find](https://scholar.google.com/scholar?q=Hangfan+Zhang%2C+Zhiyao+Cui%2C+Xinrun+Wang%2C+Qiaosheng+Zhang%2C+Zhen+Wang%2C+Dinghao+Wu%2C+and+Shuyue+Hu%2E+2025%2E+If+multi%2Dagent+debate+is+the+answer%2C+what+is+the+question%3F+Preprint%2C+arXiv%3A2502%2E08788%2E+%E2%80%94+%5BarXiv%3A250)
52. Xiutian Zhao, Ke Wang, and Wei Peng. 2024. An electoral approach to diversify llm-based multi-agent collective decision-making. Preprint, arXiv:2410.15168. [find](https://scholar.google.com/scholar?q=Xiutian+Zhao%2C+Ke+Wang%2C+and+Wei+Peng%2E+2024%2E+An+electoral+approach+to+diversify+llm%2Dbased+multi%2Dagent+collective+decision%2Dmaking%2E+Preprint%2C+arXiv%3A2410%2E15168%2E)

*Updated 2 November 2026*