Binding-Specific Relearning Savings for Test-Time Continual Learning

Title: Binding-Specific Relearning Savings for Test-Time Continual Learning

标题：针对测试时持续学习的绑定特定重学习节省

Abstract: When a fact becomes harder to elicit from a language model, has the model lost it, or has it merely become less accessible? Parameter-updating test-time continual learning agents are usually evaluated by current output accuracy; we ask whether that measurement captures how prior experience shapes later updates.

摘要：当一个事实变得难以从语言模型中提取时，是模型已经遗忘了它，还是它仅仅变得难以访问了？参数更新的测试时持续学习智能体通常通过当前的输出准确率进行评估；我们探讨这种衡量方式是否捕捉到了先前的经验如何塑造后续更新。

We test whether learning a specific factual binding produces a later relearning advantage beyond familiarity with its entity, answer vocabulary, format, or query slot. In Qwen2.5-1.5B, we compare three matched, counterbalanced histories: LEARNED receives the correct binding, CONTROL receives matched exposure without it, and WRONG receives a competing relation-valid answer in the same slot.

我们测试了学习特定的事实绑定是否会产生超出对实体、答案词汇、格式或查询槽位熟悉程度之外的后续重学习优势。在 Qwen2.5-1.5B 模型中，我们比较了三种匹配且平衡的历史记录：LEARNED 接收正确的绑定，CONTROL 接收匹配但无该绑定的暴露，而 WRONG 在同一槽位接收一个竞争性的关系有效答案。

After an identical rehearsal-free continual fine-tuning stream, LEARNED reacquires the target faster than CONTROL at a prespecified checkpoint of partial forgetting. WRONG shows no positive advantage over CONTROL, while its comparison with LEARNED provides slot-matched corroboration, subject to possible competitor interference.

在经过相同的无排练持续微调流后，在预设的部分遗忘检查点，LEARNED 比 CONTROL 更快地重新获取了目标。WRONG 相较于 CONTROL 没有表现出正向优势，而它与 LEARNED 的比较提供了槽位匹配的佐证，尽管可能受到竞争干扰的影响。

The advantage remains positive after adjustment for measured pre-relearning behavior. In a secondary descriptive conversion using an unpaired never-seen pool, prior learning reduces the optimizer updates required for restoration by about 18%. Current behavioral accuracy can therefore underestimate the lasting effect of previously acquired experience.

在针对测量的重学习前行为进行调整后，该优势依然保持正向。在利用未配对的从未见过的数据池进行的二次描述性转换中，先前的学习使恢复所需的优化器更新减少了约 18%。因此，当前的各种行为准确率可能会低估先前习得经验的持久影响。