Large language models simulate intersectional synthetic identities with a budget of one to two dimensions

• URL: http://arxiv.org/abs/2608.23005v1
• Date: Mon, 24 Aug 2026 09:07:51 GMT
• Title: Large language models simulate intersectional synthetic identities with a budget of one to two dimensions
• Abstract summary: We test demographic-persona methods against every real intersectional subgroup across 15 waves of Pew's American Trends Panel.<n>In real respondents, subgroup opinion is approximately the additive sum of its single-identity components, yet grows 2.5x more distinctive as identities intersect.
• Score: 5.10573774891006
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models are increasingly used as synthetic survey respondents, promising cheap access to rare intersectional populations. We test standard demographic-persona methods against every real intersectional subgroup across 15 waves of Pew's American Trends Panel -- 21 million simulated response distributions from eight models. In real respondents, subgroup opinion is approximately the additive sum of its single-identity components, yet grows 2.5x more distinctive as identities intersect. Simulated respondents show no such composition: a single feature explains a two-feature persona's responses better than the additive combination in 75-82% of subgroups, and a third feature adds almost nothing. This collapse survives every prompting strategy we test. Additionally, the feature models retain is chosen nearly blindly -- except that they systematically discard race and religion, the strongest real drivers of opinion. Synthetic samples offer intersectional personas but represent one identity at a time.

Related papers

• Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure [51.736723807086385]
  Population-marginal agreement is evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.<n>On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons.
  arXiv  Detail & Related papers  (2026-09-07T10:22:22Z)
• When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses [4.327699139300454]
  Large language models (LLMs) are increasingly used as synthetic users, stand-ins for human respondents whose simulated answers feed product, policy, and market decisions.<n>We ask when this substitution is valid and when it fails, and package the answer as an evaluation framework for intelligent synthetic-user systems.<n>A single protocol, run across four models spanning two families and an 8B-to-frontier capability range, is applied to two independent domains of real human-response data.<n>Every model is benchmarked against a suite of non-LLM baselines fit on held-out human data.
  arXiv  Detail & Related papers  (2026-07-28T23:43:00Z)
• The One-Word Census: Answer-Choice Conformity Across 44 Language Models [3.7734715043126488]
  We characterize convergence of 31 single-turn prompts, each naming a category with many valid one-word answers.<n>We score each model by answer-choice surprisal: the average $-log2$ probability of its answers under the pooled answers of all other models.<n> Persona- and community-tuned models are the most divergent; the newest mainline flagships are the most conformist.
  arXiv  Detail & Related papers  (2026-07-14T14:12:05Z)
• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• From Self to Other: Evaluating Demographic Perspective-Taking in LLM Hate Speech Annotation [5.762370982168011]
  Persona-conditioned Large Language Models (models prompted to adopt a specific demographic identity) have been proposed as a way to simulate diverse perspectives at scale.<n>We evaluate three aspects of human social judgement: (i) whether personas from different groups disagree in human-like ways (inter-group disagreement), (ii) whether they become more sensitive when content targets their own identity (in-group sensitivity), and (iii) whether they can accurately predict how another group would react (vicarious prediction).<n>Our results show that no model consistently captures all three dimensions, and performance is highly model-dependent and does not emerge reliably from
  arXiv  Detail & Related papers  (2026-06-04T15:09:58Z)
• Response Time Enhances Alignment with Heterogeneous Preferences [49.69696266152175]
  We show that augmenting preference datasets with a simple, secondary signal can restore identifiability of the population's average preference.<n>Our results bring promises and open up new opportunities for future data-collection pipelines.
  arXiv  Detail & Related papers  (2026-05-07T22:05:23Z)
• The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models [12.654067061944074]
  Applications based on large language models (LLMs) require population diversity among agents.<n>We identify a pervasive failure mode we term emphPersona Collapse: agents each assigned a distinct profile nonetheless converge into a narrow behavioral mode, producing a homogeneous simulated population.
  arXiv  Detail & Related papers  (2026-04-27T17:01:48Z)
• No Single Best Model for Diversity: Learning a Router for Sample Diversity [69.53166985556759]
  In this paper, we study methods to elicit a comprehensive set of valid responses.<n>We introduce textbfdiversity coverage, a metric that measures the total quality scores assigned to each textbfunique answer.<n>Per each prompt, there exists a model that outperforms all other models significantly at generating a diverse answer set.
  arXiv  Detail & Related papers  (2026-04-02T17:58:37Z)
• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond) [90.45301024940329]
  Language models (LMs) often struggle to generate diverse, human-like creative content.<n>We introduce Infinity-Chat, a large-scale dataset of 26K diverse, real-world, open-ended user queries.<n>We present a large-scale study of mode collapse in LMs, revealing a pronounced Artificial Hivemind effect.
  arXiv  Detail & Related papers  (2025-10-27T03:16:21Z)
• DisCo: Reinforcement with Diversity Constraints for Multi-Human Generation [60.741022906593685]
  DisCo is the first RL-based framework to directly optimize identity diversity in multi-human generation.<n>DisCo fine-tunes flow-matching models via Group-Relative Policy Optimization.<n>On the DiverseHumans Testset, DisCo achieves 98.6 Unique Face Accuracy and near-perfect Global Identity Spread.
  arXiv  Detail & Related papers  (2025-10-01T19:28:51Z)
• Intersectional Bias in Causal Language Models [0.0]
  We examine emphGPT-2 and emphGPT-NEO models, ranging in size from 124 million to 2.7 billion parameters. We conduct an experiment combining up to three social categories - gender, religion and disability - into unconditional or zero-shot prompts. Our results confirm earlier tests conducted with auto-regressive causal models, including the emphGPT family of models.
  arXiv  Detail & Related papers  (2021-07-16T03:46:08Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.