Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation
Not on the map. Why?
Abstract (arXiv)
We 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. It 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 the 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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 19 references that are in the map. First posted on arXiv 12 Jul 2026.
Builds on
9 of 19 references.
References · 9
- 2023Whose Opinions Do Language Models Reflect?cited by 773
- 2024Large language models that replace human participants can harmfully misportray and flatten identity groupscited by 144
- 2023Aligning Language Models to User Opinionscited by 99
- 2022Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contestcited by 98
- 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 97
- 2025LLM Generated Persona is a Promise with a Catchcited by 81
- 2024Virtual Personas for Language Models via an Anthology of Backstoriescited by 51
- 2024Few-shot Personalization of LLMs with Mis-aligned Responsescited by 32
- 2025Deep Binding of Language Model Virtual Personas: a Study on Approximating Political Partisan Misperceptionscited by 9
Built on by
Not cited yet.