←首頁

    Alignment

    安全 · 可解釋性 · 治理

    Signals

    CurvDelta: Low-Curvature Delta Modeling For Surgical Learning and Unlearning

    A central challenge in adapting large language models (LLMs) is capability preservation: an adaptation can achieve its target while degrading general capabilities. We introduce CurvDelta, a scalable framework that incorporates the preservation constraint into the parameterization of the model update. By analyzing the local geometry of…

    arXiv2026年11月18日

    Mechanistic Critics for Sample-Efficient NPU Design-Space Exploration

    NPU design-space exploration for LLM inference mainly relies on an expensive simulator that often returns only scalar feedback such as latency and power. Such feedback can rank evaluated configurations, but gives little information for deciding why a configuration is slow or which architecture parameter should be changed next. This…

    arXiv2026年11月18日

    Aligning AI Teams

    Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two software-engineering tasks (sepsis triage, a news recommender)…

    arXiv2026年11月13日

    SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

    Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a language model on the decision that lets an action through, so the decision depends on a model that may read the attacker's text and adds model…

    arXiv2026年11月4日