Liwei Jiang

Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability

HieraSuite: A Holistic Toolkit for Building Versatile System-User Instruction Hierarchy

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life

PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Interactive AI Agents

AI Debate Aids Assessment of Controversial Claims

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior

CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring (the Lack of) Cultural Knowledge of LLMs

Can Language Models Reason about Individualistic Human Values and Preferences?

SafetyAnalyst: Interpretable, transparent, and steerable LLM safety moderation