Tastes without distinction: silicon samples and the synthetic construction of tastes

arXiv:2606.30085 · cs.CL, econ.GN, q-fin.EC · Submitted 2026-06-29 · Read on arXiv

cs.CL, econ.GN, q-fin.EC

Submitted: 2026-06-29

Updated: 2026-08-30

Terminology

• Fidelity — 34× in this paper · explained in 2 episodes
• Alignment — 11× in this paper · explained in 1 episode
• Survey of Public Participation in the Arts — 4× in this paper
• Benchmark — 3× in this paper · explained in 2 episodes
• Algorithmic Bias — 2× in this paper · explained in 1 episode
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Age Gradients — 1× in this paper · explained in 1 episode
• Agent-based modeling — 1× in this paper · explained in 1 episode
• Digital Twin — 1× in this paper · explained in 5 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Homogenization — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Polypersona: Persona-Grounded LLM for Synthetic Survey Responses
• Questioning the Survey Responses of Large Language Models
• In Silico Sociology: Forecasting COVID-19 Polarization with Large Language Models
• ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context
• Evaluating Large Language Model Biases in Persona-Steered Generation
• Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science Research

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering