Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations Paper • 2505.18466 • Published May 6
BiasDora: Exploring Hidden Biased Associations in Vision-Language Models Paper • 2407.02066 • Published Oct 3, 2024
Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement Paper • 2601.21864 • Published Jun 27
Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations Paper • 2608.26576 • Published Aug 31
Global Voices, Local Biases: Socio-Cultural Prejudices across Languages Paper • 2310.17586 • Published Oct 26, 2023
Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models Paper • 2407.02067 • Published Jul 2, 2024
Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis Paper • 2407.02030 • Published Jul 2, 2024
Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs Paper • 2605.01224 • Published May 2