arXiv AI August 5, 2026 By Seth Grief-Albert, Jessica Bo, Difan Jiao, Ashton Anderson

Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulation

arXiv:2608. 03044v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate human opinions, but prior work reports conflicting results: some studies find promising alignment with human survey data, while others find persona collapse and weak demographic sensitivity.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 29

Instruction-Tuned Language Models Cannot Sample from Distributions They Can Describe

arXiv:2607. 25292v1 Announce Type: new Abstract: Silicon sampling uses language models as proxies for human survey respondents, treating each model call as an independent draw from the persona's response distribution.

By Chaemin Jang, Dongman Lee, Jihee Kim

llms fine-tuning benchmarks safety

arXiv AI

Jul 14

Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation

arXiv:2607. 10628v1 Announce Type: cross Abstract: We present Anamnesis, an interactive system for demographically controllable survey simulation using large language models.

By Song-Ze Yu, Joseph Suh, Serina Chang, David M. Chan

llms multimodal

Hugging Face Trending Papers

Aug 6

Mind the Gaps: Mixture-of-Minds for Human Simulation

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.

llms rag benchmarks safety

arXiv AI

Aug 7

Mind the Gaps: Mixture-of-Minds for Human Simulation

arXiv:2608. 06115v1 Announce Type: new Abstract: Predicting how a population will answer a new question is a long-standing goal.

By Pranav Dahiya

llms rag benchmarks safety

arXiv AI

Jul 31

When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses

arXiv:2607. 26348v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as synthetic users, stand-ins for human respondents whose simulated answers feed product, policy, and market decisions.

By Zihan Chen, Di Zhu, Lei Nico Zheng

llms benchmarks

arXiv AI

Jun 12

LLMs Can Better Capture Human Judgments--With the Right Prompts

arXiv:2606. 12754v1 Announce Type: cross Abstract: Are large language models (LLMs) bad at capturing human judgment?

By Danica Dillion, Chen Cecilia Liu, Baihui Wang, Daniele Barolo, Tanmay Rajore, Niket Tandon, Pranathi Ravikumar, Kurt Gray

llms safety

Related stories

Instruction-Tuned Language Models Cannot Sample from Distributions They Can Describe

Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation

Mind the Gaps: Mixture-of-Minds for Human Simulation

Mind the Gaps: Mixture-of-Minds for Human Simulation

When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses

LLMs Can Better Capture Human Judgments--With the Right Prompts