CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification

Yian Wang, Yuen Chen, Agam Goyal, Hari Sundaram. CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 11893-11914, Association for Computational Linguistics, 2026. [doi]

References

No references recorded for this publication.

Cited by

No citations of this publication recorded.