Transformer 可以学习它们从未见过的规则:超越插值的计算证明
Transformers Can Learn Rules They've Never Seen: Proof of Computation Beyond Interpolation
AI总结:
本文通过两个实验展示,Transformer 能够学习未在训练中直接观察到的规则结构,通过多步约束传播和符号推导,证明了其超越插值的能力。
摘要:
在大语言模型辩论中,核心问题是Transformer能否推断训练中未出现的规则,或是否所有泛化都归因于相似性插值。我们通过两个受控设置测试了仅插值假设:一个通过构造和证明排除插值,另一个要求模型输出中间符号推导而非仅最终答案。在实验1中,使用具有纯XOR转移规则的单元格自动机,移除特定局部输入模式进行训练;由于XOR线性不可分,每个被排除模式的最近邻有相反标签,因此基于相似性的预测器在被排除区域失败。然而,双层Transformer能恢复该规则(最佳100%;47/60次收敛运行),并通过电路提取识别XOR计算。性能依赖于多步约束传播:不展开时准确率与输出偏置匹配(63.1%),而软展开达到96.7%。在实验2中,研究整数上的符号运算链,其中一对运算符被排除;模型必须以证明式格式输出中间步骤和最终答案。在所有49个排除对中,Transformer超越了所有插值基线(平均41.8%,最高78.6%;平均KRR 4.3%;KNN和MLP在每对上得分为0%),而移除中间步骤监督会降低性能。结合标准Transformer块可实现精确局部布尔规则的构造,这些结果提供了存在证明,表明Transformer能够学习未在训练中直接观察到的规则结构并明确表达,排除了仅插值假设中最强的架构形式:即Transformer原则上无法发现和传达未见的规则,同时留有在大规模语言训练中此类行为出现的时间。
英文摘要:
A central question in the debate over large language models is whether transformers can learn rules they have never seen, or whether they can only interpolate: predict new cases from their similarity to training examples. We test this in a controlled setting where interpolation provably fails, so success can only come from computation beyond interpolation. We train small transformers to predict the rollout of a cellular automaton whose update rule is pure XOR, and remove one entry of the rule's truth table from all direct supervision. The missing entry's output is never shown to the model; its only trace is indirect, as wrong values corrupt visible predictions at later timesteps. Because XOR parity flips whenever one input bit is changed, every one-bit neighbour of the missing entry carries the opposite label, and we prove that similarity-based predictors, including nearest-neighbour, kernel, and Gaussian-process methods, are forced to the wrong answer. A two-layer transformer can nevertheless recover the missing entry, and circuit extraction confirms it computes XOR exactly. Ablations show the recovery depends on gradient signal propagating through multi-step prediction, and a second, structurally unrelated benchmark on symbolic operator chains exhibits the same capacity under ordinary autoregressive training. Together with a constructive proof that a standard transformer block can implement exact local Boolean rules, these results provide an existence proof that transformers can learn rule structure not directly observed in training and express it explicitly. This rules out the strongest architectural form of the interpolation-only account, the claim that transformers cannot in principle discover and communicate unseen rules, while leaving open when such behaviour arises in large-scale language training.
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。