activity
20242026
collaborators

13 papers

cs.LG2026

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…

cs.CL2026

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…

cs.AI2026

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…

cs.CL2025

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-…

cs.AI2025

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…

cs.CR2025

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…