Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails 文章

ArXiv CS.CL2026-06-05NEWSen作者: Marco Antonio Stranisci, A Pranav, Rossana Damiano, Christian Hardmeier, Anne Lauscher
查看原文 →
关系图谱

Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails · 相关技术

暂无数据