Our projects

Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving (AAAI 2022)

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models...

Balancing gender bias in job advertisements with text-level bias mitigation(Frontiers in big Data 2022)

Despite progress towards gender equality in the labor market over the past few decades, gender segregation in labor f...

Conformalized Fairness via Quantile Regression(Neurips 2022)

Algorithmic fairness has received increased attention in socially sensitive domains. While rich literature on mean fa...

Debiasing with Sufficient Projection: A General Theoretical Framework for Vector Representations(NAACL 2024)

Pre-trained vector representations in natural language processing often inadvertently encode undesirable social biase...