Skip to content
conftrace_
2025 ICML ICML 2025

Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Senyu Han, Hongchuan Zeng, Kai Yu, Lu Chen

Topics

Artificial Intelligence > Core AI > Foundation Models Artificial Intelligence > Core AI > Interpretability Artificial Intelligence > Core AI > Large Language Models

Keywords

attention head parameter efficiency large language model functional pathway inference masking
Download PDF