works on
large language models 1model realignment 1on-policy distillation 1prompt robustness 1safety alignment 1

From the 1 of 5 linked papers with an AI index.

most citedMCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment

Yongjian Guo, Wanlun Ma, Lingyu Shen +2

The paper introduces Routing-based On-Policy Distillation (ROPD), a method for safely realigning large language models that resists malicious prompt templates while preserving the…