8 papers
DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment
Tianzhuo Yang, Shaoheng Yan, Lin Lu +5
Safety alignment teaches language models to refuse harmful requests, yet the internal accessibility of hazardous concepts can retain traces of earlier training. Can checkpoints wit…
AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents
Tianzhuo Yang, Zirui Mi, Yantao Huang +4
Safety alignment for large language models (LLMs) in conversational settings is largely framed around whether to answer or refuse a request. In agentic settings, however, the same…
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
Lichao Wang, Zhaoxing Ren, Tianzhuo Yang +4
As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents u…
MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
Tianzhuo Yang, Zihan Shen, Zirui Mi +7
Action-conditioned world models are increasingly used as scalable simulators for robot learning, yet current evaluations provide limited evidence that their predictions are reliabl…
VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
Jiawei Chen, Tianzhuo Yang, Guoxi Zhang +3
Aligning Large Language Models (LLMs) with nuanced human values remains a critical challenge, as existing methods like Reinforcement Learning from Human Feedback (RLHF) often handl…
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
Guoxi Zhang, Jiawei Chen, Tianzhuo Yang +4
As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategicall…
AI Deception: Risks, Dynamics, and Controls
Boyuan Chen, Sitong Fang, Jiaming Ji +56
As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an…
A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs
Guoxi Zhang, Jiawei Chen, Tianzhuo Yang +3
The increasing prevalence of large language models (LLMs) is influencing global value systems. However, these models frequently exhibit a pronounced WEIRD (Western, Educated, Indus…