CRISP: Using Sparse Autoencoders for Persistent Concept Unlearning in Neural Networks
Tomer Ashuach, Dana Arad, Aaron Mueller, Martin Tutek, Yonatan Belinkov. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Read the full article4d ago1 min readenInsight
You might also wanna read
Dispersion loss counteracts embedding condensation to improve small language model generalization
chenliu-1996.github.io·13d ago
HOLA: Adding an Exact Memory Cache to Linear-Attention Language Models Improves Long-Context Recall
arxiv.org·13d agoHOLA: Adding an Exact Memory Cache to Linear-Attention Language Models Improves Long-Context Recall
arxiv.org·13d ago
Cartridges: Training smaller KV caches via self-study to replace in-context learning in LLMs
arxiv.org·15d agoCartridges: Training smaller KV caches via self-study to replace in-context learning in LLMs
arxiv.org·15d ago
DOPD: A Dual On-policy Distillation Method to Address Privilege Illusion in LLM and VLM Training
arxiv.org·16d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.