{"slug": "elias-in-the-lighthouse-again-diagnosing-low-diversity-in-llm-stories", "title": "Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories", "summary": "A paper submitted to arXiv on 26 May 2026 found that 11 words appear in 88.3% of LLM-generated stories, based on 20,000 stories sampled from four current models across five prompts. The recurring tokens include names (Elias, Mara, Elara), settings (lighthouses) and professions (clockmaker, librarian), and the paper reports little difference between models; these tokens are rare in published literature and pre-training data but appear in preference data likely used by all current models. The authors attribute the pattern to the disproportionate impact of small datasets combined with powerful alignment algorithms.", "body_md": "# Computer Science > Computation and Language\n\n  [Submitted on 26 May 2026]\n\n# Title:Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories\n\n[View PDF](https://arxiv.org/pdf/2605.26492)\n\n[HTML (experimental)](https://arxiv.org/html/2605.26492v1)\n\nAbstract:LLM-generated stories are a popular use case, but they show very low variability. We sample 20,000 total stories from four current models using five prompts. We find that 11 words occur in 88.3% of generated stories, with little difference between models. These words include names (Elias, Mara, Elara), settings (lighthouses), and professions (clockmaker, librarian). These tokens do not often occur in published literature nor pre-training data, but they are found in preference data that is likely to have been used by all current models. Surprisingly, these \"lighthouse\" stories are infrequent when compared with the average post-training story, much of which contains references to copyrighted characters or adult content. This result demonstrates the potentially disproportionate impact of small datasets combined with powerful alignment algorithms.\n    \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/elias-in-the-lighthouse-again-diagnosing-low-diversity-in-llm-stories", "canonical_source": "https://arxiv.org/abs/2605.26492", "published_at": "2026-10-19 22:33:04+00:00", "updated_at": "2026-10-19 22:45:58.084833+00:00", "lang": "en", "topics": ["large-language-models", "generative-ai", "ai-research", "natural-language-processing"], "entities": ["arXiv", "Elias", "Mara", "Elara"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/elias-in-the-lighthouse-again-diagnosing-low-diversity-in-llm-stories", "markdown": "https://wpnews.pro/news/elias-in-the-lighthouse-again-diagnosing-low-diversity-in-llm-stories.md", "text": "https://wpnews.pro/news/elias-in-the-lighthouse-again-diagnosing-low-diversity-in-llm-stories.txt", "jsonld": "https://wpnews.pro/news/elias-in-the-lighthouse-again-diagnosing-low-diversity-in-llm-stories.jsonld"}}