{"slug": "what-and-whose-knowledge-measuring-epistemic-diversity-in-large-language-models", "title": "What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models", "summary": "A first systematic study of epistemic diversity in large language models, testing 27 LLMs on 155 topics across 12 countries and generating 1.7M responses and 70M individual claims, found that epistemic diversity has increased substantially over the past three years but that every system remains less diverse than a search baseline, according to the arXiv paper \"What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models\" (arXiv:2510.04226v7, revised 31 Aug 2026). The study reports that retrieval-augmented generation can improve diversity, that larger models are counterintuitively less diverse than smaller ones, and that LLM parametric knowledge systematically reflects English over local-language knowledge for country-specific topics.", "body_md": "# Computer Science > Computation and Language\n\n  [Submitted on 5 Oct 2025 (\n\n[v1](https://arxiv.org/abs/2510.04226v1)), last revised 31 Aug 2026 (this version, v7)]\n# Title:What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models\n\n[View PDF](https://arxiv.org/pdf/2510.04226)\n\n[HTML (experimental)](https://arxiv.org/html/2510.04226v7)\n\nAbstract:Large language models (LLMs) are increasingly used as primary knowledge sources, yet their epistemic diversity - defined as the diversity of real-world claims in their outputs - has never been measured. Low epistemic diversity would pose a risk of knowledge collapse as homogeneous LLMs mediate a shrinking in the range of accessible information over time. The dominant paradigm is that overall LLM diversity is low, but this is always with respect to a single point in time, with no reference baseline or consideration for variation across countries. We address this gap in knowledge by performing the first systematic study of epistemic diversity in LLMs across time and cultural context, testing 27 LLMs on 155 topics covering 12 countries, resulting in 1.7M responses and 70M individual claims. We find that epistemic diversity has increased substantially over the past three years, a positive counter to recent diversity pessimism. However, despite progress, we find that every system is less diverse than a search baseline. This gap is not uniform: RAG can improve diversity, while large models are counterintuitively less diverse than smaller ones. Moreover, LLM parametric knowledge systematically reflects English over local-language knowledge for country specific topics. Together, these results demonstrate that while progress on epistemic diversity is tangible, it is insufficient and unevenly distributed.\n    \n\n## Submission history\n\nFrom: Dustin Wright [\n[view email](https://arxiv.org/show-email/0c2d6b8d/2510.04226)]\n\n**Sun, 5 Oct 2025 14:29:15 UTC (305 KB)**\n\n[\\[v1\\]](https://arxiv.org/abs/2510.04226v1)\n**Tue, 7 Oct 2025 16:07:31 UTC (807 KB)**\n\n[\\[v2\\]](https://arxiv.org/abs/2510.04226v2)\n**Wed, 8 Oct 2025 07:35:57 UTC (807 KB)**\n\n[\\[v3\\]](https://arxiv.org/abs/2510.04226v3)\n**Thu, 30 Oct 2025 14:52:48 UTC (807 KB)**\n\n[\\[v4\\]](https://arxiv.org/abs/2510.04226v4)\n**Tue, 11 Nov 2025 18:13:57 UTC (820 KB)**\n\n[\\[v5\\]](https://arxiv.org/abs/2510.04226v5)\n**Wed, 28 Jan 2026 13:27:36 UTC (826 KB)**\n\n[\\[v6\\]](https://arxiv.org/abs/2510.04226v6)\n**[v7]** Mon, 31 Aug 2026 12:37:31 UTC (226 KB)\n\n### Current browse context:\n\ncs.CL\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/what-and-whose-knowledge-measuring-epistemic-diversity-in-large-language-models", "canonical_source": "https://arxiv.org/abs/2510.04226", "published_at": "2026-09-26 11:58:16+00:00", "updated_at": "2026-09-26 12:31:46.796167+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "natural-language-processing", "ai-safety", "artificial-intelligence"], "entities": ["arXiv", "Dustin Wright"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/what-and-whose-knowledge-measuring-epistemic-diversity-in-large-language-models", "markdown": "https://wpnews.pro/news/what-and-whose-knowledge-measuring-epistemic-diversity-in-large-language-models.md", "text": "https://wpnews.pro/news/what-and-whose-knowledge-measuring-epistemic-diversity-in-large-language-models.txt", "jsonld": "https://wpnews.pro/news/what-and-whose-knowledge-measuring-epistemic-diversity-in-large-language-models.jsonld"}}