这篇论文发现了模型训练中规则自然遗忘的规律，并且能预测和控制——破坏容易恢复难，对理解LLM行为很有启发。
论文发现小型语言模型在预训练中学会的代词-性别规则（准确率0.94）会在3500步后自然消失，尽管训练数据仍包含该规则。这种未在损失曲线上反映的反转现象称为natural ungrokking。规则存留由支持频率预测：在2个语料、3个预算、3个种子的16次未干预运行中，支持频率决定规则命运。该动态出现在公开Pythia检查点中，遗忘顺序按模型规模排序。控制不对称：反转支持证据可破坏规则，但即使注入450倍支持也无法恢复。
Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining
Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0.94 by step 925). By step 3,500 the same model scores near zero on the same probes, although the rule's evidence is still in the training data. We call this within-run reversal natural ungrokking: the corpus decides, with no trace in the loss curve, which learned rules a model keeps. Which rules survive is predictable from one corpus statistic: how often the training stream shows the rule winning. Across un-intervened runs (two corpora, three budgets, three seeds), support frequency decides a rule's fate; the data-to-parameter ratio only modulates how deeply a doomed rule falls. The same emerge-then-collapse dynamics appear in public Pythia checkpoints, collapse depth ordered by model scale as predicted. The forgetting is a displacement: a competing surface pattern out-competes the rule, and the log-probability margin between them crosses zero within 100 training steps of the behavioral collapse. Control over this fate is asymmetric: the same edit that destroys a rule on demand cannot restore it. Flipping support to counter-evidence in place kills the rule with monotone dose-response in two unrelated rules; but injecting support back, even to 450 times the level that naturally sustains it, buys no recovery. Every confirmatory threshold and prediction was pre-registered before the data it governed was read.