4 papers · 1 filter
AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent
Weidi Luo, Qiming Zhang, Yihao Quan +5
Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn in…
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
Haoran Lu, Luyang Fang, Ruidong Zhang +47
Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment…
AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
Weidi Luo, Shenghong Dai, Xiaogeng Liu +4
The rapid advancements in Large Language Models (LLMs) have enabled their deployment as autonomous agents for handling complex tasks in dynamic environments. These LLMs demonstrate…
Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models
Weidi Luo, He Cao, Zijing Liu +5
With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key…