← Search

Jiamu Zheng

1 accepted papers

2025

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

ICLR 2025poster

Collaborative learning of large language models (LLMs) has emerged as a new paradigm for utilizing private data from different parties to guarantee efficiency and privacy. Meanwhile, Knowledge Editing (KE) for LLMs has also garnered increased attention due to its ability to manipulate the behaviors o…