1 citations · 1 across the 5 of their papers we have counts for
6 papers
CheatBench: Measuring Reward Gaming in AI Agents
Long Phan, Stephen K. Yang, Jason J. Lim +10
Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and controlled e…
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan +3
Large language models are increasingly deployed as autonomous agents serving users on behalf of companies, placing them in settings where user and deployer interests can conflict.…
Mirage Probes: How Vision Models Fake Visual Understanding
Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao +5
Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores with…
Proactive defense against LLM Jailbreak
Weiliang Zhao, Jinjun Peng, Daniel Ben-Levi +2
The proliferation of powerful large language models (LLMs) has necessitated robust safety alignment, yet these models remain vulnerable to evolving adversarial attacks, including m…
Diversity Helps Jailbreak Large Language Models
Weiliang Zhao, Daniel Ben-Levi, Wei Hao +2
We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generat…
Learning to Rewrite: Generalized LLM-Generated Text Detection
Ran Li, Wei Hao, Weiliang Zhao +2
Large language models (LLMs) present significant risks when used to generate non-factual content and spread disinformation at scale. Detecting such LLM-generated content is crucial…