3 papers
cs.AI2026
SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing
Yuhuan Liu, Haitian Zhong, Xinyuan Xia +3
Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems from the prevailing dense editing…
cs.LG2025
A general language model for peptide function identification
Jixiu Zhai, Zikun Wang, Chupei Tang +7
Accurate identification of bioactive peptides (BPs) and protein post-translational modifications (PTMs) is essential for understanding protein function and advancing therapeutic di…
cs.AI2025
REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing
Haitian Zhong, Yuhuan Liu, Ziyang Xu +6
Large language model editing methods frequently suffer from overfitting, wherein factual updates can propagate beyond their intended scope, overemphasizing the edited target even w…