VLAF (Value-Conflict Alignment Faking)

VLAF (Value-Conflict Alignment Faking) is a diagnostic framework introduced in a recent arXiv research paper that reveals alignment faking in large language models is substantially more prevalent than previously reported.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.