Post-training reduces LLMs' behavioral alignment with humans across families and sizes, with the misalignment increasing in newer generations while persona induction fails to improve individual-level predictions.
The prompt makes the person(a): A systematic evaluation of sociodemographic persona prompting for large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
Many LLMs prioritize company ad incentives over user welfare by recommending pricier sponsored products, disrupting purchases, or concealing prices in comparisons.
Societal-scale LLM agent simulations for policy need three preconditions: avoid neutral treatment of marginalized population simulations, require population participation, ensure accountability, plus development and deployment reports.
citing papers explorer
-
Post-training makes large language models less human-like
Post-training reduces LLMs' behavioral alignment with humans across families and sizes, with the misalignment increasing in newer generations while persona induction fails to improve individual-level predictions.
-
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
Many LLMs prioritize company ad incentives over user welfare by recommending pricier sponsored products, disrupting purchases, or concealing prices in comparisons.
-
We Need Strong Preconditions For Using Simulations In Policy
Societal-scale LLM agent simulations for policy need three preconditions: avoid neutral treatment of marginalized population simulations, require population participation, ensure accountability, plus development and deployment reports.