Story

arxiv_cs_cl ยท Oct 23, 2026 ยท paper

Source brief

Principled Nonlinear Concept Erasure and Steering

arxiv.orgOct 23, 2026
original source linked

In brief

Learned representations often encode sensitive attributes, such as gender or race, that may be undesirable or unsafe to retain. Concept erasure aims to remove this information while preserving task-relevant content. E...

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items