论文

模型合并对涌现能力的影响:保留、无法创造、更快稀释

On Emergent Capabilities and Model Merging

精选理由

想把两个模型权重合并凑出新能力?这篇论文用三个模型家族证明涌现能力合不出来,错位反而会跟着保留。

一篇 arXiv 论文研究了模型合并(对微调检查点和适配器权重做算术运算来拼接能力)对涌现能力的影响,即那些从未被显式训练目标覆盖的行为。

正文

研究在激活预言机(activation oracles)和涌现错位模型两个独立测试床上进行,覆盖三个模型家族。结果显示:当两个父模型都携带某涌现能力时,合并能保留它,例如两个错位检查点合并后在全混合比例范围内保留大部分错位。

但合并无法创造超出父模型叠加的涌现能力,两个单任务预言机的任意加权合并都达不到联合训练预言机的审计能力。当只有一方携带该能力时,合并对其稀释速度快于伴随的已训练能力,多数设置下差距显著。

原文 · arXiv cs.LG

On Emergent Capabilities and Model Merging

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.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「各国 AI 监管法案、合规治理与主权算力政策」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:模型合并、涌现能力、AI安全、微调,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Luca Zhou, Emanuele Rodolà),经 AITOP 多维评分管线结构化提炼。