SOURCE-LINKED INTELLIGENCE

On Emergent Capabilities and Model Merging

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic on their weights that assembles capabilities cheaply. We ask what this operation does to emergent capabilities: behaviors an artifact carries that were never an explicit training target. Studying two independent testbeds (activation oracles and emergent-misaligned models) across three model families, we find that the answer is threefold. First, merging preserves an emergent capability that both parents carry: merging two misaligned checkpoints

Read original source ↗ Open in workspace

recordType

paper

region

Global