主钥假说:通过线性子空间对齐实现跨模型能力转移
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
AI总结:
本文提出主钥假说,通过线性子空间对齐实现跨模型能力转移,无需重新训练,实验显示在不同模型规模上显著提升性能。
摘要:
我们研究是否可以在不重新训练的情况下将训练后的能力跨模型转移,重点在于不同模型规模间的转移。我们提出了主钥假说,即模型能力对应于低维潜在子空间中的方向,通过线性对齐在不同模型间可转移。基于此假说,我们引入UNLOCK框架,通过对比具备和不具备特定能力的源变体激活值提取能力方向,通过低秩线性变换与目标模型对齐,并在推理时应用以激发特定行为。实验显示,在推理行为(如链式思维和数学推理)上,不同模型规模间均显著提升性能。例如,将CoT推理从Qwen1.5-14B转移到Qwen1.5-7B在MATH上提升12.1%;将数学推理方向从Qwen3-4B-Base转移到Qwen3-14B-Base使AGIEval Math准确率从61.1%提升至71.3%,超过14B后训练模型的67.8%。我们的分析表明,转移的成功依赖于预训练中学习的能力,而我们的干预通过使输出分布更接近成功推理轨迹来放大潜在能力。
英文摘要:
We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master Key Hypothesis, which states that model capabilities correspond to directions in a low-dimensional latent subspace that induce specific behaviors and are transferable across models through linear alignment. Based on this hypothesis, we introduce UNLOCK, a training-free and label-free framework that extracts a capability direction by contrasting activations between capability-present and capability-absent Source variants, aligns it with a Target model through a low-rank linear transformation, and applies it at inference time to elicit the behavior. Experiments on reasoning behaviors, including Chain-of-Thought (CoT) and mathematical reasoning, demonstrate substantial improvements across model scales without training. For example, transferring CoT reasoning from Qwen1.5-14B to Qwen1.5-7B yields an accuracy gain of 12.1% on MATH, and transferring a mathematical reasoning direction from Qwen3-4B-Base to Qwen3-14B-Base improves AGIEval Math accuracy from 61.1% to 71.3%, surpassing the 67.8% achieved by the 14B post-trained model. Our analysis shows that the success of transfer depends on the capabilities learned during pre-training, and that our intervention amplifies latent capabilities by sharpening the output distribution toward successful reasoning trajectories.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。