Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs

发布

2026年04月20日

采集 2026年04月20日 06:45

学术前沿 6.7 分 — Resource-efficient framework removing unsafe subnetworks

原文： cs.LG updates on arXiv.org

评分 6.7 · 来源：cs.LG updates on arXiv.org · 发布于 2026-04-20

评分依据：Resource-efficient framework removing unsafe subnetworks

EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs

Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing