Jiliang Tang

PI-Hunter uncovers hidden prompt injection vulnerabilities in LLM agents that traditional defenses miss, revealing a critical gap in current security practices.

Latent reasoning models often take shortcuts to achieve high accuracy, and stronger supervision, while mitigating this, paradoxically restricts the diversity of their latent representations.

LLMs may ace the test, but their uncertainty estimates are far from perfect, raising serious concerns about their reliability in high-stakes educational assessments.