LLM silicon surrogates for arts participation surveys exhibit positive liking bias, lose taste relationality, and fail to preserve known social space alignments.
Title resolution pending
8 Pith papers cite this work, alongside 348 external citations. Polarity classification is still indexing.
8
Pith papers citing it
348
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
StereoTales shows that all tested LLMs emit harmful stereotypes in open-ended stories, with associations adapting to prompt language and targeting locally salient groups rather than transferring uniformly across languages.
Audience segmentation restores heterogeneity in LLM social simulations, with moderate granularity and data-driven selection often improving structural and predictive fidelity on U.S. climate-opinion data while no configuration dominates all evaluation dimensions.
In 50 LLM measurement tasks from 27 top-journal papers, LLM outputs are often central to claims yet validation is limited, mostly convergent, and frequently incomplete.
LLM personas exhibit model-dependent personality effects on color choices and context-driven chart preferences, limiting their use as direct substitutes for human participants in visualization design.
Centralized matching mechanisms outperform free negotiation in stability and efficiency with LLM agents, who also report preferences truthfully more often than humans, though not always in line with strategy-proofness predictions.
LLM embeddings enable strong retrodiction of masked GSS opinions via cross-validation and external validation but only modest performance on entirely unasked opinions.
Proposes AI-driven simulations for literary-historical experiments and reports preliminary text-generation results claiming the first limited in-distribution outputs matching human novels.
citing papers explorer
-
Not-quite-human tastes: the stylized omnivorousness of LLM survey surrogates
LLM silicon surrogates for arts participation surveys exhibit positive liking bias, lose taste relationality, and fail to preserve known social space alignments.
-
StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
StereoTales shows that all tested LLMs emit harmful stereotypes in open-ended stories, with associations adapting to prompt language and targeting locally salient groups rather than transferring uniformly across languages.
-
Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach
Audience segmentation restores heterogeneity in LLM social simulations, with moderate granularity and data-driven selection often improving structural and predictive fidelity on U.S. climate-opinion data while no configuration dominates all evaluation dimensions.
-
Validating LLMs in social science: Epistemic threats and emerging norms
In 50 LLM measurement tasks from 27 top-journal papers, LLM outputs are often central to claims yet validation is limited, mostly convergent, and frequently incomplete.
-
When Do LLM Personas Support Visualization Design? A Cross-Model Study of Color Assignment and Chart Choice
LLM personas exhibit model-dependent personality effects on color choices and context-driven chart preferences, limiting their use as direct substitutes for human participants in visualization design.
-
Do Matching Mechanisms Work with LLM Agents?
Centralized matching mechanisms outperform free negotiation in stability and efficiency with LLM agents, who also report preferences truthfully more often than humans, though not always in line with strategy-proofness predictions.
-
AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction
LLM embeddings enable strong retrodiction of masked GSS opinions via cross-validation and external validation but only modest performance on entirely unasked opinions.
-
AI as a Tool for Simulation-Based Experiments in Literary Studies
Proposes AI-driven simulations for literary-historical experiments and reports preliminary text-generation results claiming the first limited in-distribution outputs matching human novels.