Richer persona descriptions in LLMs cause systematic contraction of representational and behavioral diversity, with simple age-gender prompts outperforming complex ideal customer profiles in downstream accuracy.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
LLMs display prompt-sensitive risk behavior and a linearly decodable realization-status signal in Gemma's residual stream, yet activation steering along this direction fails to shift downstream risk choices.
A scoping review of 81 articles finds generative AI widely applied to persona development with 61% resource sharing but 45% lacking evaluation and frequent GPT-only use, proposing guidelines to address circularity and reduced human oversight.
NormCoRe is a replication-by-translation framework that maps human subject studies onto multi-agent AI environments, showing AI normative judgments on fairness differ from human baselines and vary with model choice and persona language.
citing papers explorer
-
How Well Do Large Language Models Capture Human Personality?
Richer persona descriptions in LLMs cause systematic contraction of representational and behavioral diversity, with simple age-gender prompts outperforming complex ideal customer profiles in downstream accuracy.
-
Representation Without Control: Testing the Realization Effect in Language Models
LLMs display prompt-sensitive risk behavior and a linearly decodable realization-status signal in Gemma's residual stream, yet activation steering along this direction fails to shift downstream risk choices.
-
Creating and Evaluating Personas Using Generative AI: A Scoping Review of 81 Articles
A scoping review of 81 articles finds generative AI widely applied to persona development with 61% resource sharing but 45% lacking evaluation and frequent GPT-only use, proposing guidelines to address circularity and reduced human oversight.
-
Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-Agent AI
NormCoRe is a replication-by-translation framework that maps human subject studies onto multi-agent AI environments, showing AI normative judgments on fairness differ from human baselines and vary with model choice and persona language.