4 papers
RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection
Yan Hong, Wei Li, Kedong Xiu +6
Knowledge injection updates pretrained MLLMs with new factual or domain-specific knowledge, but fitting full authoritative answers can cause drift in non-updated behavior. Online d…
LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models
Yan Hong, Kedong Xiu, Wei Li +6
We study controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models, aiming to increase non-refusal target-response behavior while preserving gener…
SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…
Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Yanjiang Liu, Shuhen Zhou, Yaojie Lu +6
Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs). However, most existing methods focus on isolated safety flaws, l…