On Emergent Capabilities and Model Merging
Quick summary
arXiv:2609.24504v1 Announce Type: cross Abstract: 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
Key takeaways
- arXiv:2609.24504v1 Announce Type: cross Abstract: 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.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments