Introduces GenAI agent framework for auditing personalization algorithms via synthetic accounts with fixed personas, applied to X post-2024 election showing amplification of toxic and right-leaning content varying by ideology.
ISBN 979-8-4007-0704-9
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
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.
Marketplace Evaluation uses repeated-interaction simulations to assess information access systems with marketplace-level metrics such as retention and market share that complement traditional accuracy measures.
Large-scale experiment with 1440 task executions finds dynamic routing of coordination strategies achieves near-best quality scores across models and classes but does not reliably identify exact winners.
Large-scale analysis of 59,808 annotations shows persona prompting produces convergent captions but systematically varying justifications tied to socioeconomic and political attributes in multimodal LLM urban perception outputs.
The paper maps LLM agent architectures onto a six-level continuum and argues that higher levels can enable simulation of emergent social phenomena while requiring attention to reproducibility and ethical issues.
citing papers explorer
-
Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale
Introduces GenAI agent framework for auditing personalization algorithms via synthetic accounts with fixed personas, applied to X post-2024 election showing amplification of toxic and right-leaning content varying by ideology.
-
Analyzing Persona Effects in Generated Explanations from Multimodal LLM Agents in Urban Perception
Large-scale analysis of 59,808 annotations shows persona prompting produces convergent captions but systematically varying justifications tied to socioeconomic and political attributes in multimodal LLM urban perception outputs.