arXiv - CSCL: "TaCo: Targeted Concept Removal in Output Embeddin…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

TaCo: Targeted Concept Removal in Output Embeddings for NLP via Information Theory and Explainability. (arXiv:2312.06499v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2312.06499 #arXiv #NLProc

Jan 14, 2024, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation