On Emergent Capabilities and Model Merging

2026-09-21

AI Summary

研究通过模型合并方法探讨了新兴能力的变化，发现合并操作对这些未明确训练的目标行为有三种主要影响。

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 parents carry: merging two misaligned checkpoints retains most of their broad misalignment across the whole mixing range. Second, merging cannot create an emergent capability that is superadditive in its parents: no weighted merge of two single-task oracles reaches the jointly-trained oracle's auditing ability. Third, when only one parent carries the capability, merging dilutes it faster than the trained capability that accompanies it: the gap is significant in most settings. In short, emergent behaviors of an artifact do not compose the way its trained capability does.

Problem

• emergent capabilities
• model merging
• fine-tuned checkpoints
• adapters
• weights arithmetic

Innovation

• model merging
• emergent capabilities
• superadditive
• capability dilution
• trained capability