Tag
This paper audits six large language models for gender stereotyping across English, Korean, Chinese, and Japanese, anchoring against human baselines. It finds that LLM stereotyping often exceeds human cross-country variation and can compound across languages, introducing a four-pattern framework to characterize such behaviors.
This paper proposes a neuron-level intervention method to identify gender-specific neurons in language models (feminine, masculine, gender-neutral) and steer sentence generation toward a target gender form while preserving meaning, with experiments showing precise control and bias mitigation.
This paper presents the first bias evaluation of multimodal speech recognition models, finding significant accuracy differences across gender and ethnicity when pairing faces with audio, with implications for fairness in AI systems.
Proposes EquiSumm, a gender bias-aware framework for inclusive tweet summarization that ensures representation of opinions from different gender groups, addressing demographic fairness in automated summarization.
This paper investigates how chain-of-thought prompting affects gender bias in large language models, finding that it does not consistently reduce bias and that apparent improvements stem from superficial compliance rather than genuine understanding.
A study found that identical AI-generated resumes for a man and a woman received significantly different evaluations, with the woman's CV more likely to be doubted for competence and trustworthiness. This reflects broader gender biases in AI usage perceptions and may exacerbate the AI adoption gap.