13 papers
Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
Mickel Liu, Liwei Jiang, Yancheng Liang +4
Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities. This s…
Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
Taylor Sorensen, Benjamin Newman, Jared Moore +5
Language model post-training has enhanced instruction-following and performance on many downstream tasks, but also comes with an often-overlooked cost on tasks with many possible v…
ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
Hongjue Zhao, Haosen Sun, Jiangtao Kong +8
Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time…
AI Debate Aids Assessment of Controversial Claims
Salman Rahman, Sheriff Issaka, Ashima Suvarna +11
As AI grows more powerful, it will increasingly shape how we understand the world. But with this influence comes the risk of amplifying misinformation and deepening social divides-…
HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
Xuhui Zhou, Hyunwoo Kim, Faeze Brahman +9
AI agents are increasingly autonomous in their interactions with human users and tools, leading to increased interactional safety risks. We present HAICOSYSTEM, a framework examini…
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Salman Rahman, Liwei Jiang, James Shiffer +7
Multi-turn interactions with language models (LMs) pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work…