{"slug": "mind-the-gaps-mixture-of-minds-for-human-simulation", "title": "Mind the Gaps: Mixture-of-Minds for Human Simulation", "summary": "Researchers introduced Anacreon, an audience simulation model that achieves a state-of-the-art individual-level ordinal alignment of 0.775 on a large external survey, targeting individual-level predictions within a narrow domain. Built on a Gemma 4 12B base, Anacreon learns authorship embeddings, clusters a qualitative corpus, and trains dedicated adapters per cluster, while reducing prompt brittleness and positive bias. The work aims to draw aggregate insight from faithfully simulated individuals.", "body_md": "# Computer Science > Artificial Intelligence\n\n[Submitted on 6 Aug 2026]\n\n# Title:Mind the Gaps: Mixture-of-Minds for Human Simulation\n\n[View PDF](/pdf/2608.06115)\n\n[HTML (experimental)](https://arxiv.org/html/2608.06115v1)\n\nAbstract:Predicting how a population will answer a new question is a long-standing goal. Statistical methods succeed at the level of the mass but falter at the level of the individual. Large language model simulators inherit this gap. They recover a population's central tendencies while flattening its heterogeneity, and they carry social biases and prompt brittleness that distort individual predictions. This paper introduces Anacreon, an audience simulation model that targets the individual level within a narrow, well-specified domain. Anacreon learns an authorship embedding that separates individuals, clusters a real qualitative corpus around seed people, and trains a dedicated adapter for each cluster, a mixture of minds, on a Gemma~4 12B base. It harvests demographics, psychological traits, and survey responses from public text, and augments each record with a chain-of-emotion. It reduces prompt brittleness by shuffling response options and reduces positive bias by balancing the training distribution. On a large, externally sourced survey, Anacreon reaches a state-of-the-art ordinal alignment of 0.775, the individual-level accuracy measure on which the field has converged, with a small residual bias. The work is a step toward drawing aggregate insight from faithfully simulated individuals.\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/))# 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))# 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))# 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/mind-the-gaps-mixture-of-minds-for-human-simulation", "canonical_source": "https://arxiv.org/abs/2608.06115", "published_at": "2026-08-10 14:58:31+00:00", "updated_at": "2026-08-10 15:11:34.277708+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "machine-learning"], "entities": ["Anacreon", "Gemma 4 12B"], "alternates": {"html": "https://wpnews.pro/news/mind-the-gaps-mixture-of-minds-for-human-simulation", "markdown": "https://wpnews.pro/news/mind-the-gaps-mixture-of-minds-for-human-simulation.md", "text": "https://wpnews.pro/news/mind-the-gaps-mixture-of-minds-for-human-simulation.txt", "jsonld": "https://wpnews.pro/news/mind-the-gaps-mixture-of-minds-for-human-simulation.jsonld"}}