Skip to content
AI Atlas
Graph explorer Paper

Research network around Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking

Papers, authors, the models and datasets they describe. Click a node to inspect it, double-click to expand, drag to pan, wheel to zoom.

1 nodes · 0 edges

No research network relations recorded for Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking