1 citations · 1 across the 5 of their papers we have counts for
3 papers · 1 filter
REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories
Hanwen Zhang, Enyi Jiang, Ruike Zhu +2
Chain-of-thought (CoT) generation offers an opportunity to intervene before a reasoning model completes its answer. But does the point at which risk is easiest to detect also offer…
CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
Chengxiao Wang, Enyi Jiang, Xiaojing Liao +1
Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safety tuning may affect model responses to both harmful and benign…
When Behavioral Safety Evaluation Fails: A Representation-Level Perspective
Enyi Jiang, Anders Gjølbye, Yibo Jacky Zhang +1
Safety evaluation of large language models (LLMs) is largely behavioral: a model is certified safe when it refuses harmful requests and answers benign ones. But refusing on the pro…