Tag
This paper examines how LLM-based agents construct human stereotypes on an open social platform, finding that bias manifests as a dynamic discourse process rather than isolated model outputs.
This paper introduces S2D, a systematic framework to evaluate regional bias in LLMs from abstract stereotypes to concrete social decisions, covering all 34 provincial-level regions of China. Results show that regional bias is prevalent, systematic, and consequential, with patterns linked to regional economic indicators.
New research shows that LLMs can develop their own biases from experience and stereotype job applicants more than humans, raising concerns about AI in hiring.
Introduces a cost-efficient human-LLM collaborative annotation framework to construct EspanStereo, a Spanish-language stereotype dataset covering multiple Spanish-speaking countries, enabling more culturally grounded bias evaluation in LLMs.
This paper introduces VETO, a benchmark to quantify 'misfired alignment' where LLMs avoid correct inferences due to safety training, and finds that all tested models exhibit such failures while humans do not.