How LLMs Are Persuaded: A Few Attention Heads, Rerouted

ArXi:2605.09314v1 Announce Type: new Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A small set of mid-layer attention heads almost entirely determines the model's answer. These heads write answer options into a low-dimensional polyhedron, with options occupying distinct vertices.