---
title: "UNSC-Bench — paper by Nangia et al. (2026)"
description: "The authors test this through UNSC-Bench, a benchmark in which a model, given the text of a UN Security Council draft, must… 37 references."
authors: ["Ayush Nangia", "Aman Gokrani", "Ruggero Marino Lazzaroni"]
year: 2026
venue: "Proceedings of the First Workshop on Multilingual Multicultural Evaluation"
source: "https://aclanthology.org/2026.mme-main.10/"
doi: "10.18653/v1/2026.mme-main.10"
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/nangia-2026-unsc-bench-evaluating-llm-diplomatic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/nangia-2026-unsc-bench-evaluating-llm-diplomatic/)

[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/55/) / UNSC-Bench: Evaluating LLM Diplomatic Role-Playing Through UN Security Council Vote Prediction

# UNSC-Bench: Evaluating LLM Diplomatic Role-Playing Through UN Security Council Vote Prediction

**Authors:** Ayush Nangia, Aman Gokrani and Ruggero Marino Lazzaroni · **Year:** 2026 · **Venue:** [Proceedings of the First Workshop on Multilingual Multicultural Evaluation](https://md.research.elamur.ai/free/en/venues/mme/) ([Workshop on Multilingual Multicultural Evaluation 2026](https://md.research.elamur.ai/free/en/venues/mme/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.mme-main.10/) · [PDF](https://aclanthology.org/2026.mme-main.10.pdf) · [DOI 10.18653/v1/2026.mme-main.10](https://doi.org/10.18653/v1/2026.mme-main.10) · [OpenAlex](https://openalex.org/W7140080971)

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

## Summary
The paper asks whether large language models can convincingly take on the diplomatic perspective of a specific state. The authors test this through UNSC-Bench, a benchmark in which a model, given the text of a UN Security Council draft, must predict how each of the five permanent members (P5) voted. The dataset was assembled from CR-UNSC, the DPPA veto records and the UN Digital Library. It covers 469 resolutions from 1947 to 2025 and includes the drafts in English, Chinese, French and Russian. The authors evaluated 26 LLMs (29 configurations with thinking variants) in two zero-shot conditions: a neutral prompt and an explicit country role-play prompt.

Without a role, models mostly vote yes and match no P5 member's voting profile. With a role, accuracy rises with general capability as measured by MMLU-Pro. Models built in a given country gain no edge when playing that country. The prompt language can shift predictions considerably, mainly for the rarer no and abstain votes. These results matter for anyone using LLMs in policy simulation or in multilingual geopolitical applications.

## Key points
- **Dataset:**
  - 469 resolutions yielding 2,345 P5 vote instances.
  - 211 vetoed drafts (45%) and 258 adopted resolutions (55%).
  - The draft text actually put to a vote is used wherever it is available.
  - Russia (22.6%) and the US (19.4%) have by far the highest shares of no votes.
- **Text recovery:**
  - Corrupted older PDFs were recovered with DeepSeek-OCR.
  - Fewer than 20 missing official translations were generated with DeepSeek V3.2-exp.
- **No home advantage:**
  - All five Chinese models score their best Macro F1 on the US role, not on China.
  - GPT-5 achieves the highest China-role score of any model.
  - French models (e.g., Mistral Large) and Russian models (GigaChat-20B-A3B, Vistral-24B) also peak on roles other than their home country.
- **Language sensitivity:**
  - For the US role, Kimi K2 [instruct] scores a no-class F1 of 0.00 with Russian prompts versus 0.69 with French prompts.
  - DeepSeek V3.2-exp stays comparatively stable across languages.
  - Thinking variants partly reduce the instability.
- **Limitations:**
  - All experiments use a single zero-shot prompt template per condition.
  - Models receive no context such as earlier votes or debate records.
  - Memorization of historical votes cannot be fully ruled out.

*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 (7): [🖥️ 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 · [🤝 Political Science and International Relations](https://md.research.elamur.ai/free/en/shelves/social-sciences/political-science-and-international-relations/) · 206 works · [🎓 Education](https://md.research.elamur.ai/free/en/shelves/social-sciences/education/) · 212 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Ayush Nangia, Aman Gokrani and Ruggero Marino Lazzaroni. 2026. UNSC-Bench: Evaluating LLM Diplomatic Role-Playing Through UN Security Council Vote Prediction. Proceedings of the First Workshop on Multilingual Multicultural Evaluation.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{nangia2026unsc,
  title = {{UNSC-Bench: Evaluating LLM Diplomatic Role-Playing Through UN Security Council Vote Prediction}},
  author = {Ayush Nangia, Aman Gokrani and Ruggero Marino Lazzaroni},
  booktitle = {Proceedings of the First Workshop on Multilingual Multicultural Evaluation},
  year = {2026},
  doi = {10.18653/v1/2026.mme-main.10},
  url = {https://doi.org/10.18653/v1/2026.mme-main.10}
}
```

- [← previous Unrequited Emotions: Investigating the Gaps in Motivation and Practice in Speech Emotion Recognition Research](https://md.research.elamur.ai/free/en/papers/wong-2026-unrequited-emotions-investigating-gaps-motivation/)
- [next → Unveiling Inherent Visual Grounding in Multimodal LLMs for Text-Rich Images](https://md.research.elamur.ai/free/en/papers/zhou-2026-unveiling-inherent-visual-grounding-multimodal/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/55/)

## References

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

1. Muhammad Farid Adilazuarda, Sagnik Mukherjee, Pradhyumna Lavania, Siddhant Shivdutt Singh, Alham Fikri Aji, Jacki O’Neill, Ashutosh Modi, and Monojit Choudhury. 2024. [Towards measuring and modeling “culture” in LLMs: A survey](https://md.research.elamur.ai/free/en/papers/adilazuarda-2024-measuring-modeling-culture-llms-survey/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Lan…
2. Gati V Aher, Rosa I. Arriaga, and Adam Tauman Kalai. 2023. Using large language models to simulate multiple humans and replicate human subject studies. In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 337–371. PMLR… [find](https://scholar.google.com/scholar?q=Gati+V+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+In+Proceedings+of+the+40th+International+Confere)
3. Anthropic. 2025. Claude sonnet 4.5 system card. Technical Report. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2025%2E+Claude+sonnet+4%2E5+system+card%2E+Technical+Report%2E)
4. Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, Quyet V. Do, Yan Xu, and Pascale Fung. 2023. [A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity](https://md.research.elamur.ai/free/en/papers/bang-2023-multitask-multilingual-multimodal-evaluation-chatgpt/). In Proceedings of…
5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, et a… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
6. Pinzhen Chen, Simon Yu, Zhicheng Guo, and Barry Haddow. 2024. Is it good data for multilingual instruction tuning or just bad multilingual evaluation for large language models? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9706–9726, Miami, Florida,… [find](https://scholar.google.com/scholar?q=Pinzhen+Chen%2C+Simon+Yu%2C+Zhicheng+Guo%2C+and+Barry+Haddow%2E+2024%2E+Is+it+good+data+for+multilingual+instruction+tuning+or+just+bad+multilingual+evaluation+for+large+language+models%3F+In+Proceedings+of+the+2)
7. 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. 2025. [CulturalBench: A robust, diverse and challenging benchmark for measuring LMs’ cultural knowledge through human-AI red-teami…](https://md.research.elamur.ai/free/en/papers/chiu-2025-culturalbench-robust-diverse-challenging-benchmark/)
8. Jonghyeon Choi, Yeonjun Choi, Hyun chul Kim, and Beakcheol Jang. 2025. “As Eastern Powers, I Will Veto”: An investigation of nation-level bias of large language models in international relations. Preprint, arXiv:2511.10695. — [arXiv:2511.10695](https://arxiv.org/abs/2511.10695) [find](https://scholar.google.com/scholar?q=Jonghyeon+Choi%2C+Yeonjun+Choi%2C+Hyun+chul+Kim%2C+and+Beakcheol+Jang%2E+2025%2E+%E2%80%9CAs+Eastern+Powers%2C+I+Will+Veto%E2%80%9D%3A+An+investigation+of+nation%2Dlevel+bias+of+large+language+models+in+international+relations%2E+Prep)
9. DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenhao Xu, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, et al. 2025. [DeepSeek-v3.2: Pushing the frontier of open large la…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/)
10. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. [The Llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). Preprint, arXiv:2407.21783.
11. Esin Durmus, Karina Nyugen, 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. 2023. [Towards measuring t…](https://md.research.elamur.ai/free/en/papers/durmus-2023-towards-measuring-representation-subjective-global/)
12. Seán Fobbe, Lorenzo Gasbarri, and Niccolò Ridi. 2024. Corpus of resolutions: Un security council (cr- unsc). [find](https://scholar.google.com/scholar?q=Se%C3%A1n+Fobbe%2C+Lorenzo+Gasbarri%2C+and+Niccol%C3%B2+Ridi%2E+2024%2E+Corpus+of+resolutions%3A+Un+security+council+%28cr%2D+unsc%29%2E)
13. GigaChat Team, Valentin Mamedov, et al. 2025. GigaChat family: Efficient Russian language modeling through mixture of experts architecture. Preprint, arXiv:2506.09440. [find](https://scholar.google.com/scholar?q=GigaChat+Team%2C+Valentin+Mamedov%2C+et+al%2E+2025%2E+GigaChat+family%3A+Efficient+Russian+language+modeling+through+mixture+of+experts+architecture%2E+Preprint%2C+arXiv%3A2506%2E09440%2E)
14. Tiancheng Hu and Nigel Collier. 2024. [Quantifying the persona effect in LLM simulations](https://md.research.elamur.ai/free/en/papers/hu-2024-quantifying-persona-effect-llm-simulations/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10289–10307, Bangkok, Thailand. Association for Computational Linguistics.
15. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. Preprint, arXiv:2310.06825. [find](https://scholar.google.com/scholar?q=Albert+Q%2E+Jiang%2C+Alexandre+Sablayrolles%2C+Arthur+Mensch%2C+Chris+Bamford%2C+Devendra+Singh+Chaplot%2C+Diego+de+las+Casas%2C+Florian+Bressand%2C+Gianna+Lengyel%2C+Guillaume+Lample%2C+Lucile+Saulnier%2C+et+al%2E+2023%2E+Mis)
16. Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of experts. Preprint, arXiv:2401.04088. [find](https://scholar.google.com/scholar?q=Albert+Q%2E+Jiang%2C+Alexandre+Sablayrolles%2C+Antoine+Roux%2C+Arthur+Mensch%2C+Blanche+Savary%2C+Chris+Bamford%2C+Devendra+Singh+Chaplot%2C+Diego+de+las+Casas%2C+Emma+Bou+Hanna%2C+Florian+Bressand%2C+et+al%2E+2024%2E+Mixtral+)
17. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). Preprint, arXiv:2001.08361.
18. Kimi Team, Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, et al. 2025. [find](https://scholar.google.com/scholar?q=Kimi+Team%2C+Yifan+Bai%2C+Yiping+Bao%2C+Guanduo+Chen%2C+Jiahao+Chen%2C+Ningxin+Chen%2C+Ruijue+Chen%2C+Yanru+Chen%2C+Yuankun+Chen%2C+Yutian+Chen%2C+et+al%2E+2025%2E)
19. [Kimi k2: Open agentic intelligence](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k2-open-agentic/). arXiv:2507.20534. Preprint, Bryan Li, Samar Haider, and Chris Callison-Burch. 2024a. This land is Your, My land: Evaluating geopolitical bias in language models through territorial disputes. In Proceedings of the 2024 Conference of the North American Chapter of th…
20. Junyi Li, Charith Peris, Ninareh Mehrabi, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, and Rahul Gupta. 2024b. The steerability of large language models toward data-driven personas. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational… [find](https://scholar.google.com/scholar?q=Junyi+Li%2C+Charith+Peris%2C+Ninareh+Mehrabi%2C+Palash+Goyal%2C+Kai%2DWei+Chang%2C+Aram+Galstyan%2C+Richard+Zemel%2C+and+Rahul+Gupta%2E+2024b%2E+The+steerability+of+large+language+models+toward+data%2Ddriven+personas%2E+In+P)
21. Yueqing Liang, Liangwei Yang, Chen Wang, Congying Xia, Rui Meng, Xiongxiao Xu, Haoran Wang, Ali Payani, and Kai Shu. 2025. Benchmarking LLMs for political science: A United Nations perspective. Preprint, arXiv:2502.14122. — [arXiv:2502.14122](https://arxiv.org/abs/2502.14122) [find](https://scholar.google.com/scholar?q=Yueqing+Liang%2C+Liangwei+Yang%2C+Chen+Wang%2C+Congying+Xia%2C+Rui+Meng%2C+Xiongxiao+Xu%2C+Haoran+Wang%2C+Ali+Payani%2C+and+Kai+Shu%2E+2025%2E+Benchmarking+LLMs+for+political+science%3A+A+United+Nations+perspective%2E+Prepri)
22. Junho Myung, Nayeon Lee, Yi Zhou, Jiho Jin, Rifki Afina Putri, Dimosthenis Antypas, Hsuvas Borkakoty, Eunsu Kim, Carla Perez-Almendros, Abinew Ali Ayele, Víctor Gutiérrez-Basulto, Yazmín Ibáñez García, Hwaran Lee, Shamsuddeen Hassan Muhammad, Kiwoong Park, Anar Sabuhi Rzayev, Nina White, Seid Muhie… — [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/)
23. Tarek Naous, Michael J Ryan, Alan Ritter, and Wei Xu. 2024. [Having beer after prayer? measuring cultural bias in large language models](https://md.research.elamur.ai/free/en/papers/naous-2023-having-beer-after-prayer-measuring/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16366–16393, Bangkok, Thailand. Associatio…
24. Aleksandr Nikolich, Konstantin Korolev, Artem Shelmanov, and Igor Yaroslavtsev. 2024. Vikhr: The family of open-source instruction-tuned large language models for Russian. Preprint, arXiv:2405.13929. 2024. Escalation risks from language models in military and diplomatic decision-making. In Proceedin… — [arXiv:2405.13929](https://arxiv.org/abs/2405.13929) [find](https://scholar.google.com/scholar?q=Aleksandr+Nikolich%2C+Konstantin+Korolev%2C+Artem+Shelmanov%2C+and+Igor+Yaroslavtsev%2E+2024%2E+Vikhr%3A+The+family+of+open%2Dsource+instruction%2Dtuned+large+language+models+for+Russian%2E+Preprint%2C+arXiv%3A2405%2E13929%2E+)
25. Jonathan Rystrøm, Hannah Rose Kirk, and Scott A. Hale. 2025. Multilingual != multicultural: Evaluating gaps between multilingual capabilities and cultural alignment in LLMs. In Proceedings of the First Interdisciplinary Workshop on Observations of Misunderstood, Misguided and Malicious Use of Langua… [find](https://scholar.google.com/scholar?q=Jonathan+Rystr%C3%B8m%2C+Hannah+Rose+Kirk%2C+and+Scott+A%2E+Hale%2E+2025%2E+Multilingual+%21%3D+multicultural%3A+Evaluating+gaps+between+multilingual+capabilities+and+cultural+alignment+in+LLMs%2E+In+Proceedings+of+the+Firs)
26. Mikhail Salnikov, Dmitrii Korzh, Ivan Lazichny, Elvir Karimov, Artyom Iudin, Ivan Oseledets, Oleg Y. Rogov, Alexander Panchenko, Natalia Loukachevitch, and Elena Tutubalina. 2025. Geopolitical biases in LLMs: what are the “good” and the “bad” countries according to contemporary language models. Prep… — [arXiv:2506.06751](https://arxiv.org/abs/2506.06751) [find](https://scholar.google.com/scholar?q=Mikhail+Salnikov%2C+Dmitrii+Korzh%2C+Ivan+Lazichny%2C+Elvir+Karimov%2C+Artyom+Iudin%2C+Ivan+Oseledets%2C+Oleg+Y%2E+Rogov%2C+Alexander+Panchenko%2C+Natalia+Loukachevitch%2C+and+Elena+Tutubalina%2E+2025%2E+Geopolitical+biases+)
27. Shivalika Singh, Angelika Romanou, Clémentine Fourrier, David Ifeoluwa Adelani, Jian Gang Ngui, Daniel Vila-Suero, Peerat Limkonchotiwat, Kelly Marchisio, Wei Qi Leong, Yosephine Susanto, Raymond Ng, Shayne Longpre, Sebastian Ruder, Wei-Yin Ko, Antoine Bosselut, Alice Oh, Andre Martins, Leshem Chosh… — [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://md.research.elamur.ai/free/en/papers/singh-2025-global-mmlu-understanding-addressing-cultural/)
28. Zhi Rui Tam, Cheng-Kuang Wu, Yu Ying Chiu, Chieh-Yen Lin, Yun-Nung Chen, and Hung-yi Lee. 2025. [Language matters: How do multilingual input and reasoning paths affect large reasoning models?](https://md.research.elamur.ai/free/en/papers/tam-2025-language-matters-multilingual-input-reasoning/) Preprint, arXiv:2505.17407.
29. 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).
30. United Nations Department of Political and Peacebuilding Affairs. 2025. [find](https://scholar.google.com/scholar?q=United+Nations+Department+of+Political+and+Peacebuilding+Affairs%2E+2025%2E)
31. Security Council Data: Vetoes Since 1946. [https://psdata.un.org/](https://psdata.un.org/) dataset/DPPA-SCVETOES. Open dataset of all vetoes cast by permanent members of the UN Security Council. [↗](https://psdata.un.org/)
32. Weihong Qi, Hanjia Lyu, and Jiebo Luo. 2025. Representation bias in political sample simulations with large language models. In Companion Proceedings of the ACM on Web Conference 2025, pages 1264–1267, Sydney, NSW, Australia. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Weihong+Qi%2C+Hanjia+Lyu%2C+and+Jiebo+Luo%2E+2025%2E+Representation+bias+in+political+sample+simulations+with+large+language+models%2E+In+Companion+Proceedings+of+the+ACM+on+Web+Conference+2025%2C+pages+1264%E2%80%931267)
33. Siqi Wang, Zhengyu Chen, Bei Li, Keqing He, Min Zhang, and Jingang Wang. 2024a. Scaling laws across model architectures: A comparative analysis of dense and MoE models in large language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5583–5595… [find](https://scholar.google.com/scholar?q=Siqi+Wang%2C+Zhengyu+Chen%2C+Bei+Li%2C+Keqing+He%2C+Min+Zhang%2C+and+Jingang+Wang%2E+2024a%2E+Scaling+laws+across+model+architectures%3A+A+comparative+analysis+of+dense+and+MoE+models+in+large+language+models%2E+In+Pro)
34. Juan-Pablo Rivera, Gabriel Mukobi, Anka Reuel, Max Lamparth, Chandler Smith, and Jacquelyn Schneider. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, OpenAI. 2025. GPT-5 system card. Technical Report. [find](https://scholar.google.com/scholar?q=Juan%2DPablo+Rivera%2C+Gabriel+Mukobi%2C+Anka+Reuel%2C+Max+Lamparth%2C+Chandler+Smith%2C+and+Jacquelyn+Schneider%2E+Yubo+Wang%2C+Xueguang+Ma%2C+Ge+Zhang%2C+Yuansheng+Ni%2C+Abhranil+Chandra%2C+Shiguang+Guo%2C+Weiming+Ren%2C+OpenA)
35. Aaran Arulraj, Xuan He, Ziyan Jiang, Tianle Li, Max Ku, Kai Wang, Alex Zhuang, Rongqi Fan, Xiang Yue, and Wenhu Chen. 2024b. [MMLU-pro: A more robust and challenging multi-task language understanding benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-mmlu-pro-more-robust-challenging/). In Advances in Neural Information Processing Systems 37, pages 95266–95290, Vancouver, Can…
36. Haoran Wei, Yaofeng Sun, and Yukun Li. 2025. [DeepSeek-OCR: Contexts optical compression](https://md.research.elamur.ai/free/en/papers/wei-2025-deepseek-ocr-contexts-optical/). Preprint, arXiv:2510.18234.
37. A.3 Table 6 shows how often each permanent member vetoed a draft in our collection. Since multiple P5 members can veto the same draft, these counts reflect veto occurrences by country rather than distinct vetoed resolutions. Country Caleb Ziems, William Held, Omar Shaikh, Jiaao Chen, Zhehao Zhang, a… — [Can Large Language Models Transform Computational Social Science?](https://md.research.elamur.ai/free/en/papers/ziems-2023-large-language-models-transform-computational/)

*Updated 2 November 2026*