[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85989-en":3,"doc-seo-85989-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85989,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Anamnesis: Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation","Anamnesis is an interactive, open-source platform for demographically controllable survey simulation using large language models. Built for non-technical researchers, it enables rapid prototyping and stress-testing of survey instruments on virtual populations rather than real human subjects. The system implements the Anthology and Alterity frameworks through a unified web interface, supports open-ended generation, probabilistic demographic resampling, and multimodal image/audio surveys. Case studies replicate Pew ATP segments and emulate preferences in the New Yorker Caption Contest, matching real-world distributions more closely than persona baselines.","Anamnesis: An Open-Source  \nPlatform for Large-Scale Backstory-Conditioned Survey Simulation  \nSong-Ze Yu, Joseph Suh, Serina Chang, David M. Chan  \nUniversity of California, Berkeley  \n{vaclis,josephsuh,serinac,[davidchan}@berkeley.edu](davidchan}@berkeley.edu)  \narXiv :2607 . 10628v 1 [ cs .CL] 12 Jul 2026  \nAbstract  \nWe present Anamnesis, an interactive system for demographically controllable survey simulation using large language models. Open-source, and designed for non-technical users/researchers, Anamnesis enables the prototyping and stress-testing of survey instruments on virtual populations rather than real human subjects. The platform operationalizes the recently introduced Anthology and Alterity frameworks, which use structured narrative backstories to condition model responses, within a unified web interface.  \nIt supports open-ended generation, probabilistic demographic resampling, and multimodal (image and audio) surveys. We evaluate the system through two case studies: (1) replicating segments of Pew Research Center’s American Trends Panel (ATP) on political typology and biomedical issues and (2) emulating human preference in  \nthe New Yorker Caption Contest. In both cases, Anamnesis produces opinion distributions that more closely match real-world survey data than standard persona-prompting baselines, offering a transparent, reproducible, and open-source alternative to proprietary simulation services.  \nDemo Video: [https://www.youtube.com/](https://www.youtube.com/)[ ](https://www.youtube.com/)watch?v=j5yrnJl287g  \nPlatform site: [https://simulate.group](https://simulate.group)  \n1 Introduction  \nOpinion surveys and social polling are foundational tools for understanding human behavior, public policy, and societal trends. However, traditional humansubject research faces mounting challenges, including rising costs, declining response rates, and the logistical difficulty of reaching specific demographic subpopulations. The emergence of Large Language Models (LLMs) as “virtual personas” offers an alternative, promising the ability to prototype survey instruments and stress-test social hypotheses at a fraction of the time and cost of traditional methods. For these simulated surveys to be scientifically valid, however, models must move beyond “average” aggregate responses  \nFigure 1: Anamnesis is an interactive system for demographically controllable survey simulation using large language models. It provides a non-technical interface for Anthology, a method which approximates large-scale human studies by conditioning LLMs to representative, consistent, and diverse virtual personas. Together, these systems enable rapid prototyping and stress-testing of survey instruments on diverse virtual populations using multimodal stimuli.  \nand instead demonstrate the ability to faithfully simulate the nuanced, idiosyncratic perspectives of diverse individuals (Kang et al., 2025; Moon et al., 2024).  \nPrevious efforts to simulate human populations have primarily relied on “persona prompting,” where a model is given a short list of demographic attributes. While functional for basic tasks, this approach often yields stereotypical responses and lacks the psychological depth required for complex opinion elicitation (Cheng et al., 2023). This limitation has been addressed by the Anthology methodology (Moon et al., 2024) which utilizes rich, open-ended narrative backstories to condition model responses, and the Alterity framework (Kang et al., 2025), which explores “deep binding” to ensure LLMs simulate authentic in-group perspectives rather than out-group misperceptions (Wang et al., 2025). Despite these academic advances, the methodologies remain largely confined to siloed Python scripts. Meanwhile, commercial platforms such as Synthetic Users, Expected Parrot, andArtificial Societies (Synthetic Users, 2026; Expected Parrot, 2026; Artificial Societies, 2026) offer similar  \nsimulation capabilities but operate as closed-source, pro","cbCaidIizCZaC8r6","https://ap.wps.com/l/cbCaidIizCZaC8r6","pdf",1897380,5,1,9,"English","en",105,"# Introduction\n# Anthology: Narrative-based Virtual Persona\n# Platform Capabilities and Evaluation\n# Case Studies","[{\"question\":\"What is Anamnesis designed to do?\",\"answer\":\"Anamnesis provides an interactive system for demographically controllable survey simulation using large language models. It helps users prototype and stress-test survey instruments on virtual populations instead of recruiting real participants.\"},{\"question\":\"How does Anamnesis generate survey responses?\",\"answer\":\"It operationalizes the Anthology and Alterity frameworks by conditioning LLMs on structured narrative backstories within a unified web interface. This supports open-ended generation and demographic resampling.\"},{\"question\":\"What capabilities and evaluation settings does the platform support?\",\"answer\":\"Anamnesis supports multimodal surveys using images and audio, along with language-only generation. Evaluation uses case studies including replication of Pew Research Center ATP segments and emulation of preferences in the New Yorker Caption Contest.\"}]",1784207602,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"anamnesis-open-source-platform-for-large-scale-backstory-conditioned-survey-simulation","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/anamnesis-open-source-platform-for-large-scale-backstory-conditioned-survey-simulation/85989/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is Anamnesis designed to do?","Question",{"text":76,"@type":77},"Anamnesis provides an interactive system for demographically controllable survey simulation using large language models. It helps users prototype and stress-test survey instruments on virtual populations instead of recruiting real participants.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does Anamnesis generate survey responses?",{"text":81,"@type":77},"It operationalizes the Anthology and Alterity frameworks by conditioning LLMs on structured narrative backstories within a unified web interface. This supports open-ended generation and demographic resampling.",{"name":83,"@type":74,"acceptedAnswer":84},"What capabilities and evaluation settings does the platform support?",{"text":85,"@type":77},"Anamnesis supports multimodal surveys using images and audio, along with language-only generation. Evaluation uses case studies including replication of Pew Research Center ATP segments and emulation of preferences in the New Yorker Caption Contest.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":20,"slug":137},19,"General","general"]