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.
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.
Related stories
arXiv AI
Aug 5
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.
arXiv AI
Jun 15
OdysSim: Building Foundation Models for Human Behavior Simulation
arXiv:2606. 14199v1 Announce Type: cross Abstract: Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation.
arXiv AI
Jul 17
Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
arXiv:2510. 01171v4 Announce Type: replace-cross Abstract: Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse.
arXiv Computation and Language
Sep 22
Pretrained Persona Mixture Models and Tandem Models for Human Simulation
arXiv:2609.22607v1 Announce Type: new Abstract: We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas,...
arXiv AI
4d ago
Population Fidelity: Evaluating Population Representativeness in LLMs
The paper introduces Population Fidelity, an evaluation framework for assessing how well large language models (LLMs) represent human population attitudes. It focuses on three dimensions: group-level accuracy, between-group variation, and the structure of that variation. Using the framework, the authors replicate a prior study on machine bias and test cultural fine-tuning, finding that while fine-tuning improves overall alignment, it does not enhance representation of within-population differences.
arXiv AI
Aug 5
Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling
arXiv:2608. 02618v1 Announce Type: new Abstract: Recent studies have identified an ``Artificial Hivemind'' effect in Large Language Models (LLMs) causing models to converge on a narrow, homogenized consensus even for open questions.
arXiv Computation and Language
Sep 23
Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation
The study evaluates whether large language models (LLMs) used as synthetic personas can predict real audience responses to marketing copy. Using thousands of headline A/B tests from the Upworthy Research Archive, the authors compare a ten-persona panel grounded in real audience demographics to a no-persona zero‑shot baseline that asks the model for a typical reader’s click likelihood. Results show that the no‑persona baseline outperforms the persona‑based approach, with higher predictive validity and top‑1 accuracy, indicating that forcing the model to role‑play specific personas introduces bias and noise.
arXiv AI
Aug 25
When Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion Sensing
arXiv:2608.22438v1 Announce Type: new Abstract: Persona-conditioned large language models (LLMs) are increasingly used to simulate survey responses across diverse domains. However, apparent response...
arXiv AI
Jun 18
How Well Do Large Language Models Capture Human Personality?
arXiv:2606. 18263v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to simulate human populations via persona prompting, often under the assumptions that richer persona descriptions improve behavioral fidelity, similarly sized attribute combinations are equally simulatable, and persona definitions generalize across tasks.
arXiv AI
Jul 1
Learning by Surprise: Adaptive Mitigation of Model Collapse in Large Language Models
arXiv:2410. 12341v4 Announce Type: replace-cross Abstract: As AI-generated content increasingly populates the web, generative AI models are at growing risk of being trained on their own outputs, a process known as AI autophagy.
arXiv AI
Jul 24
More Is Not More: What Matters for Diversity in LLM Opinions?
arXiv:2607. 20429v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate diverse human opinions in open-ended tasks such as synthetic surveys, focus group modeling, and public opinion prediction.