Заголовок на английскомAlignment Faking Depends on the Value, Not Just the Model
arXiv:2611.03650v1 Announce Type: new Abstract: Language models can follow a directive when they believe they are monitored and abandon it when they believe they are not, a pattern termed Alignment Faking. Prior work establishes this for harmful-content objectives and a handful…
Кратко от AI: Главные тезисы
- arXiv:2611.03650v1 Announce Type: new Abstract: Language models can follow a directive when they believe they are monitored and abandon it when they believe they are not, a pattern termed Alignment Faking
- Prior work establishes this for harmful-content objectives and a handful…
Alignment Faking Depends on the Value, Not Just the Model
Похожие материалы
ENCARD: A Proof-Carrying Certificate-to-Action Interface for Relative-Measurement Graphs
arXiv:2611.03651v1 Announce Type: new Abstract: Geometric certificates make mathematical claims about specified estimator objects, while robotic action requires a physical transform, a service decision, and timely proof support. We present CARD, a proof-carrying interface that…
ENMCPGuard: Finding Conformance Gaps in MCP SDKs via Dual-Track Analysis and Dynamic Adjudication
arXiv:2611.03662v1 Announce Type: new Abstract: The Model Context Protocol (MCP) connects large language model agents to external tools and services through official SDKs that implement message validation and session logic. Specification constraints omitted by these SDKs may…
ENFunctional-Group Knowledge Is Structured in Language Models Before It Is Spoken
arXiv:2611.03684v1 Announce Type: new Abstract: Language models serve as the reasoning core of agents for chemistry and materials science, where they must interpret molecular structure before planning syntheses or proposing materials. Yet their outputs show only what they say,…
ENLOLPlay: Benchmarking Real-Time Visual Agents in League of Legends
arXiv:2611.03685v1 Announce Type: new Abstract: Visual agents need to coordinate reasoning and action while their environment evolves during inference. We introduce LOLPlay, a benchmark in native \emph{League of Legends} with 36 champion-specific tasks spanning resource…