Elamur Research⌕
☰
home / papers / 2026 / Localized Cultural Knowledge is Conserved and Controllable in Large Language Models

Localized Cultural Knowledge is Conserved and Controllable in Large Language Models

Paper · 2026 · Veniamin Veselovsky, Berke Argın, Benedikt Stroebl et al.

Summary

Large language models (LLMs) often answer non-English prompts as if the user lived in an English-speaking, largely American setting, even when they hold the relevant local knowledge. The authors measure this as the "explicit–implicit localization gap." This is the performance difference between prompts that name the user's country (e.g., "I live in [X]") and prompts where only the language signals the culture. They build a benchmark covering Turkish, Russian, French and Bengali, plus English, from four datasets: Names, Cities, o1-distilled and CulturalBench. They test seven models on it.

Naming the country improves localization substantially, but open-ended answers become more uniform and stereotyped. Using contrastive activation addition on Gemma2-9b-it, the authors derive steering vectors that shift outputs toward the local culture without any explicit hint. These vectors transfer across languages and tasks and keep the diversity of implicit prompting. They are also more faithful and less stereotypical, though less accurate than explicit prompting. The findings matter for interpreting cultural benchmarks and for building models that adapt to users by default.

Key points

  • Models evaluated: Aya-8b-expanse, Gemma2-9b-it, Gemma2-27b-it, Llama-3.1-8b-base, Llama-3.1-8b-it, Llama-3.1-70b-it and GPT-4o.
  • Evaluation setup: decoding uses temperature 0, except open-ended generation (temperature 1, top-p 0.9, top-k 50). Two-option questions are scored over both answer orders to cancel order bias.
  • Motivating example: GPT-4o says pumpkins are orange when asked in Japanese. It says green once Japan is explicitly mentioned.
  • Steering method: the vectors come from contrasting hinted with unhinted prompts, or translated with English prompts. Each is a single vector added at one later layer, only to newly generated tokens, and the analysis uses nnsight. The authors also report preliminary, not yet rigorously tested, evidence of a universal vector that steers outputs toward the culture of the prompt's language.
  • Limitations and release: the study covers only five languages and assumes culture maps onto language. Evaluation relies on embedding similarity and LLM-as-a-judge rather than user studies. Code and data are available at github.com/vminvsky/localization-gap.

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

🎓Princeton UniversityPrinceton · United States90 works · 39,109 citations🎓University of ChicagoChicago · United States45 works · 50,617 citations🎓École Polytechnique Fédérale de LausanneLausanne · Switzerland44 works · 7,050 citations🎓Northeastern UniversityBoston · United States57 works · 6,533 citations🔬Santa Fe InstituteSanta Fe · United States7 works · 646 citations

 Fields, topics and concepts

📚 Shelves 4The 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 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Veniamin Veselovsky, Berke Argın, Benedikt Stroebl, Chris Wendler, Robert West, James Evans, Thomas L. Griffiths and Arvind Narayanan. 2026. Localized Cultural Knowledge is Conserved and Controllable in Large Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.2141

@inproceedings{veselovsky2026localized,
  title = {{Localized Cultural Knowledge is Conserved and Controllable in Large Language Models}},
  author = {Veniamin Veselovsky, Berke Argın, Benedikt Stroebl, Chris Wendler, Robert West, James Evans, Thomas L. Griffiths and Arvind Narayanan},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2141},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2141}
}

References

82 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2024. GPT-4 technical report. Preprint, arXiv:2303.08774.
  2. Jesujoba O Alabi, Marius Mosbach, Matan Eyal, Dietrich Klakow, and Mor Geva. 2024. The hidden space of transformer language adapters. Preprint, arXiv:2402.13137. find
  3. Badr AlKhamissi, Muhammad ElNokrashy, Mai Alkhamissi, and Mona Diab. 2024. Investigating cultural alignment of large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12404–12422, Bangkok, Thailand. Association…
  4. 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). Association for Computational Linguistics. for Computational Linguistics…
  5. Hritik Bansal, Da Yin, Masoud Monajatipoor, and Kai-Wei Chang. 2022. How well can text-to-image generative models understand ethical natural language interventions? In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1358–1370, Abu Dhabi, United Arab Emir… find
  6. Alexis Conneau and Guillaume Lample. 2019. Cross-lingual language model pretraining. Proceedings of the 33rd International Conference on Neural Information Processing Systems. find
  7. Behind the Name. 2025. Behind the name: The etymology and history of first names. Accessed: 2025-01-10. find
  8. Stella Biderman, Hailey Schoelkopf, Lintang Sutawika, Leo Gao, Jonathan Tow, Baber Abbasi, Alham Fikri Aji, Pawan Sasanka Ammanamanchi, Sidney Black, Jordan Clive, Anthony DiPofi, Julen Etxaniz, Benjamin Fattori, Jessica Zosa Forde, Charles Foster, Jeffrey Hsu, Mimansa Jaiswal, Wilson Y. Lee, Haonan… find
  9. Jannik Brinkmann, Chris Wendler, Christian Bartelt, and Aaron Mueller. 2025. Large language models share representations of latent grammatical concepts across typologically diverse languages. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computat… find
  10. Egon Brunswik. 1940. Thing constancy as measured by correlation coefficients. Psychological Review, 47(1):69. find
  11. Tyler A. Chang, Catherine Arnett, Zhuowen Tu, and Benjamin Bergen. 2023. When is multilinguality a curse? language modeling for 250 high- and low-resource languages. In Conference on Empirical Methods in Natural Language Processing.
  12. 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…
  13. KuanChao Chu, Yi-Pei Chen, and Hideki Nakayama. 2025. Exploring and controlling diversity in LLM-agent conversation. In Findings of the Association Alexis Conneau, Guillaume Lample, Ruty Rinott, Adina Williams, Samuel R. Bowman, Holger Schwenk, and Veselin Stoyanov. 2018. Xnli: Evaluating cross-ling… find
  14. John Dang, Shivalika Singh, Daniel D’souza, Arash Ahmadian, Alejandro Salamanca, Madeline Smith, Aidan Peppin, Sungjin Hong, Manoj Govindassamy, Terrence Zhao, et al. 2024. Aya expanse: Combining research breakthroughs for a new multilingual frontier. arXiv preprint arXiv:2412.04261.
  15. Tim R. Davidson, Viacheslav Surkov, Veniamin Veselovsky, Giuseppe Russo, Robert West, and Caglar Gulcehre. 2024. Self-recognition in language models. Preprint, arXiv:2407.06946. find
  16. Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. Qlora: Efficient finetuning of quantized llms. Advances in neural information processing systems, 36:10088–10115.
  17. Yanping Dong, Shichun Gui, and Brian MacWhinney. 2005. Shared and separate meanings in the bilingual mental lexicon. Bilingualism: Language and Cognition, 8(3):221–238. find
  18. Clément Dumas, Chris Wendler, Veniamin Veselovsky, Giovanni Monea, and Robert West. 2025. Separating tongue from thought: Activation patching reveals language-agnostic concept representations in transformers. Preprint, arXiv:2411.08745.
  19. Jaden Fried Fiotto-Kaufman, Alexander Russell Loftus, Eric Todd, Jannik Brinkmann, Koyena Pal, Dmitrii Troitskii, Michael Ripa, Adam Belfki, Can Rager, Caden Juang, Aaron Mueller, Samuel Marks, Arnab Sen Sharma, Francesca Lucchetti, Nikhil Prakash, Carla E. Brodley, Arjun Guha, Jonathan Bell, Byron… find
  20. Clifford Geertz. 2017. The interpretation of cultures. Basic books. find
  21. Atticus Geiger, Zhengxuan Wu, Christopher Potts, Thomas Icard, and Noah D. Goodman. 2024. Finding alignments between interpretable causal variables and distributed neural representations. Preprint, arXiv:2303.02536. find
  22. Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, and Mor Geva. 2024. Patchscopes: a unifying framework for inspecting hidden representations of language models. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. JMLR.org. find
  23. Omer Goldman, Uri Shaham, Dan Malkin, Sivan Eiger, Avinatan Hassidim, Yossi Matias, Joshua Maynez, Adi Mayrav Gilady, Jason Riesa, Shruti Rijhwani, Laura Rimell, Idan Szpektor, Reut Tsarfaty, and Matan Eyal. 2025. Eclektic: a novel challenge set for evaluation of cross-lingual knowledge transfer. Pr… — [arXiv:2502.21228](https://arxiv.org/abs/2502.21228) find
  24. Srishti Gureja, Lester James Validad Miranda, Shayekh Bin Islam, Rishabh Maheshwary, Drishti Sharma, Gusti Triandi Winata, Nathan Lambert, Sebastian Ruder, Sara Hooker, and Marzieh Fadaee. 2025. M-RewardBench: Evaluating reward models in multilingual settings. In Proceedings of the 63rd Annual Meeti…
  25. Daniil Gurgurov, Tanja Bäumel, and Tatiana Anikina. 2024. Multilingual large language models and curse of multilinguality. find
  26. Christian Haerpfer, Ronald Inglehart, Alejandro Moreno, Christian Welzel, Kseniya Kizilova, Jaime Diez-Medrano, Marta Lagos, Pippa Norris, Eduard Ponarin, Björn Puranen, et al. 2020. World values survey: Round seven–country-pooled datafile. Madrid, Spain & Vienna, Austria: JD Systems Institute & WVS… find
  27. Yifei He, Alon Benhaim, Barun Patra, Praneetha Vaddamanu, Sanchit Ahuja, Parul Chopra, Vishrav Chaudhary, Han Zhao, and Xia Song. 2024. Scaling laws for multilingual language models. Preprint, arXiv:2410.12883. find
  28. William Held and Diyi Yang. 2022. Shapley head pruning: Identifying and removing interference in multilingual transformers. Preprint, arXiv:2210.05709. find
  29. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring massive multitask language understanding. Proceedings of the International Conference on Learning Representations (ICLR).
  30. Geert Hofstede. 1984. Culture’s consequences: International differences in work-related values, volume 5. sage. find
  31. Tim Hornyak. 2023. Why Japan Is Building Its Own Version of ChatGPT — scientificamerican.com. Accessed 14-10-2024. find
  32. Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. find
  33. Parameter-efficient transfer learning for nlp. In International conference on machine learning, pages 2790–2799. PMLR. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In Internatio…
  34. Robert Huben, Hoagy Cunningham, Logan Riggs Smith, Aidan Ewart, and Lee Sharkey. 2024. Sparse autoencoders find highly interpretable features in language models. In The Twelfth International Conference on Learning Representations. find
  35. Nithish Kannen, Arif Ahmad, marco Andreetto, Vinodkumar Prabhakaran, Utsav Prabhu, Adji Bousso Dieng, Pushpak Bhattacharyya, and Shachi Dave. 2024. Beyond aesthetics: Cultural competence in text-to-image models. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Ben… find
  36. Sayash Kapoor, Benedikt Stroebl, Zachary S Siegel, Nitya Nadgir, and Arvind Narayanan. 2025. AI agents that matter. Transactions on Machine Learning Research. find
  37. Nora Kassner, Philipp Dufter, and Hinrich Schütze. 2021. Multilingual LAMA: Investigating knowledge in multilingual pretrained language models. Preprint, arXiv:2102.00894.
  38. Simran Khanuja, Vivek Iyer, Claire He, and Graham Neubig. 2025. Towards automatic evaluation for image transcreation. Preprint, arXiv:2412.13717. find
  39. Simran Khanuja, Sathyanarayanan Ramamoorthy, Yueqi Song, and Graham Neubig. 2024. An image speaks a thousand words, but can everyone listen? on image transcreation for cultural relevance. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 10258–10279, Mi… find
  40. George Lakoff. 2008. Women, fire, and dangerous things: What categories reveal about the mind. University of Chicago press. find
  41. Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz, John P. Agapiou, William A. Cunningham, Peter Sunehag, Julia Haas, Raphael Koster, Edgar A. Duéñez-Guzmán, William S. Isaac, Georgios Piliouras, Stanley M. Bileschi, Iyad Rahwan, and Simon Osindero. 2024. A theory of appropriateness with appli… — [arXiv:2412.19010](https://arxiv.org/abs/2412.19010) find
  42. Molly Lewis, Aoife Cahill, Nitin Madnani, and James Evans. 2023. Local similarity and global variability characterize the semantic space of human languages. Proceedings of the National Academy of Sciences, 120(51):e2300986120. find
  43. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. 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 4582–… find
  44. Bill Yuchen Lin, Seyeon Lee, Xiaoyang Qiao, and Xiang Ren. 2021. Common sense beyond English: Evaluating and improving multilingual language models for commonsense reasoning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL-IJCNLP 2021). To appear.
  45. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. TruthfulQA: Measuring how models mimic human falsehoods. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3214–3252, Dublin, Ireland. Association for Computational Linguistics…
  46. Jack Lindsey, Wes Gurnee, Emmanuel Ameisen, Brian Chen, Adam Pearce, Nicholas L. Turner, Craig Citro, David Abrahams, Shan Carter, Basil Hosmer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persi… find
  47. Thomas Marshall, Adam Scherlis, and Nora Belrose. 2025. Refusal in llms is an affine function. Preprint, arXiv:2411.09003. — [arXiv:2411.09003](https://arxiv.org/abs/2411.09003) find
  48. Pedro Henrique Martins, Patrick Fernandes, João Alves, Nuno M. Guerreiro, Ricardo Rei, Duarte M. Alves, José Pombal, Amin Farajian, Manuel Faysse, Mateusz Klimaszewski, Pierre Colombo, Barry Haddow, José G.C. de Souza, Alexandra Birch, and André F.T. Martins. 2025. Eurollm: Multilingual language mod…
  49. Eriko Matsuki, Yasushi Hino, and Debra Jared. 2021. Understanding semantic accents in Japanese–English bilinguals: A feature-based approach. Bilingualism: Language and cognition, 24(1):137–153. find
  50. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2023. Locating and editing factual associations in GPT. Preprint, arXiv:2202.05262. find
  51. Meta AI. 2025. Llama 3.1 8b instruct. Accessed: 2025-01-10. find
  52. Julian Minder, Kevin Du, Niklas Stoehr, Giovanni Monea, Chris Wendler, Robert West, and Ryan Cotterell. 2025. Controllable context sensitivity and the knob behind it. In The Thirteenth International Conference on Learning Representations. find
  53. Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng Xin Yong, Hailey Schoelkopf, Xiangru Tang, Dragomir Radev, Alham Fikri Aji, Khalid Almubarak, Samuel Albanie, Zaid Alyafeai, Albert Webson, Edward Raff, and Colin Raffel.… — Crosslingual Generalization through Multitask Finetuning
  54. Tarek Naous, Michael J Ryan, Alan Ritter, and Wei Xu. 2024. Having beer after prayer? measuring cultural bias in large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16366–16393, Bangkok, Thailand. Associatio…
  55. OpenAI. 2024a. Government of iceland. https://openai.com/index/government-of-iceland/. [Accessed 13-10-2024]. ↗
  56. OpenAI. 2024b. GPT-4o system card. arXiv:2410.21276.
  57. Preprint, OpenAI. 2024c. OpenAI o1 system card. Preprint, arXiv:2412.16720.
  58. OpenAI. 2025. Introducing OpenAI o1 preview. Accessed: 2025-01-10. find
  59. Rait Piir. 2023. Finland’s chatgpt equivalent begins to think in estonian as well. ERR News. find
  60. Edoardo Maria Ponti, Goran Glavaš, Olga Majewska, Qianchu Liu, Ivan Vulić, and Anna Korhonen. 2020. XCOPA: A multilingual dataset for causal commonsense reasoning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2362–2376.
  61. Jirui Qi, Raquel Fernández, and Arianna Bisazza. 2023. Cross-lingual consistency of factual knowledge in multilingual language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10650–10666, Singapore. Association for Computational Linguistics.
  62. Sara Rajaee and Christof Monz. 2024. Analyzing the evaluation of cross-lingual knowledge transfer in multilingual language models. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2895–2914, St. Julian’s, Ma… find
  63. Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Turner. 2024. Steering llama 2 via contrastive activation addition. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15504–15522, Bangkok, Thaila… find
  64. Angelika Romanou, Negar Foroutan, Anna Sotnikova, Sree Harsha Nelaturu, Shivalika Singh, Rishabh Maheshwary, Micol Altomare, Zeming Chen, Mohamed A. Haggag, Snegha A, Alfonso Amayuelas, Azril Hafizi Amirudin, Danylo Boiko, Michael Chang, Jenny Chim, Gal Cohen, Aditya Kumar Dalmia, Abraham Diress, Sh… — INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
  65. Lisa Schut, Yarin Gal, and Sebastian Farquhar. 2025. Do multilingual LLMs think in english? In ICLR 2025 Workshop on Building Trust in Language Models and Applications. find
  66. Anton Schäfer, Shauli Ravfogel, Thomas Hofmann, Tiago Pimentel, and Imanol Schlag. 2024. The role of language imbalance in cross-lingual generalisation: Insights from cloned language experiments. Preprint, arXiv:2404.07982. — [arXiv:2404.07982](https://arxiv.org/abs/2404.07982) find
  67. Freda Shi, Mirac Suzgun, Markus Freitag, Xuezhi Wang, Suraj Srivats, Soroush Vosoughi, Hyung Won Chung, Yi Tay, Sebastian Ruder, Denny Zhou, Dipanjan Das, and Jason Wei. 2022. Language models are multilingual chain-of-thought reasoners.
  68. 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
  69. Shivalika Singh, Freddie Vargus, Daniel Dsouza, Börje F. Karlsson, Abinaya Mahendiran, Wei-Yin Ko, Herumb Shandilya, Jay Patel, Deividas Mataciunas, Laura OMahony, Mike Zhang, Ramith Hettiarachchi, Joseph Wilson, Marina Machado, Luisa Souza Moura, Dominik Krzemi’nski, Hakimeh Fadaei, Irem Ergun, Ife… — Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning
  70. Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, and Ji-Rong Wen. 2024. Language-specific neurons: The key to multilingual capabilities in large language models.
  71. Yan Tao, Olga Viberg, Ryan S Baker, and René F Kizilcec. 2024. Cultural bias and cultural alignment of large language models. PNAS Nexus, 3(9):346. find
  72. Alexandre Variengien and Eric Winsor. 2023. Look before you leap: A universal emergent decomposition of retrieval tasks in language models. Preprint, arXiv:2312.10091. — [arXiv:2312.10091](https://arxiv.org/abs/2312.10091) find
  73. Ashmal Vayani, Dinura Dissanayake, Hasindri Watawana, Noor Ahsan, Nevasini Sasikumar, Omkar Thawakar, Henok Biadglign Ademtew, Yahya Hmaiti, Amandeep Kumar, Kartik Kuckreja, et al. 2024. All languages matter: Evaluating LLMs on culturally diverse 100 languages. Preprint, arXiv:2411.16508. — [arXiv:2411.16508](https://arxiv.org/abs/2411.16508) find
  74. Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber. 2020. Investigating gender bias in language models using causal mediation analysis. In Advances in Neural Information Processing Systems, volume 33, pages 12388–12401. find
  75. Angelina Wang, Jamie Morgenstern, and John P Dickerson. 2025. Large language models cannot replace human participants because they cannot portray identity groups. Preprint, arXiv:2402.01908. — [arXiv:2402.01908](https://arxiv.org/abs/2402.01908) find
  76. Weixuan Wang, Barry Haddow, Minghao Wu, Wei Peng, and Alexandra Birch. 2024. Sharing matters: Analysing neurons across languages and tasks in LLMs. Preprint, arXiv:2406.09265. — [arXiv:2406.09265](https://arxiv.org/abs/2406.09265) find
  77. Chris Wendler, Veniamin Veselovsky, Giovanni Monea, and Robert West. 2024. Do Llamas work in English? On the latent language of multilingual transformers. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15366–15394.
  78. Zhaofeng Wu, Xinyan Velocity Yu, Dani Yogatama, Jiasen Lu, and Yoon Kim. 2024. The semantic hub hypothesis: Language models share semantic representations across languages and modalities. Preprint, arXiv:2411.04986. find
  79. Zhengxuan Wu, Aryaman Arora, Zheng Wang, Atticus Geiger, Dan Jurafsky, Christopher D Manning, and Christopher Potts. 2025. Reft: Representation finetuning for language models. Advances in Neural Information Processing Systems, 37:63908–63962. find
  80. Da Yin, Hritik Bansal, Masoud Monajatipoor, Liunian Harold Li, and Kai-Wei Chang. 2022. Geomlama: Geo-diverse commonsense probing on multilingual pre-trained language models. Preprint, arXiv:2205.12247. find
  81. Xiang Yue, Yueqi Song, Akari Asai, Seungone Kim, Jean de Dieu Nyandwi, Simran Khanuja, Anjali Kantharuban, Lintang Sutawika, Sathyanarayanan Ramamoorthy, and Graham Neubig. 2025. Pangea: A fully open multilingual multimodal LLM for 39 languages. Preprint, arXiv:2410.16153. *Figure 4: When prompted w… find
  82. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-bench and chatbot arena. In Thirty-seventh Conference on Neural Information Processing…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/veselovsky-2026-localized-cultural-knowledge-is-conserved/