conftrace_

harmful stereotype

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

dehumanization analysis (1) lgbtq+ individual (1) sexual interaction (1) concept vector (1) bias transfer (1) social bias mitigation (1) fairness in machine learning (1) lgbtq group (1) bias transfer hypothesis (1) pre-training bia (1)

Papers

Dehumanization of LGBTQ+ Groups in Sexual Interactions with ChatGPT NAACL 2025 Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models ACL 2022