arXiv:2512.06582cs.LGcs.AI2025-12

提出可诊断的记忆机制,揭示记忆是否真被使用。

Diagnosing Capability Preservation and Task Sensitivity in Memory Augmented Document Classifiers

  • 设计双路径模型,分离因果局部路径与关联记忆写入
  • 记忆保留率达100%,但下游性能不依赖具体记忆内容
  • 适合研究记忆机制有效性或模型可解释性的研究人员

仅靠任务准确率无法判断记忆机制是否真正保留能力、暴露样本特异性信息或对下游性能有实质贡献。本文提出受保护的QL记忆模型,从能力保留、诊断访问和任务敏感性三方面评估其特性。该模型包含因果局部路径、关联矩阵写入器和最终记忆读取器。通过受控训练流程,在9组数据集-种子条件下进行适应前后诊断及最终记忆干预。结果表明:写入器能力完全保留,适应后准确率为100%;重新分配最终矩阵导致诊断准确率下降86.3至86.9个百分点,显示对样本记忆强依赖;而自然文本宏F1变化小于0.002,说明下游性能不依赖具体记忆内容。在AG News、IMDB、Yelp Review Full上锁测试宏F1分别为90.94%、81.78%、62.63%,与紧凑基线相当。因此,能力保留、诊断访问与任务对齐应作为独立目标,需直接评估下游记忆敏感性。

原文摘要 · Abstract (English)

End task accuracy alone cannot determine whether a memory mechanism preserves an acquired capability, exposes sample-specific stored information, or contributes measurably to downstream performance. This study introduces Protected QL Memory and evaluates capability preservation, diagnostic access, and task performance sensitivity as distinct empirical properties. Protected QL Memory is a dual path document classifier combining a causal local pathway, an associative matrix writer, and a finalized memory reader. A capability-protected schedule acquires a controlled binding capability, adapts the local pathway while constraining writer degradation, trains controlled memory access, and restricts full path task fitting. Pre and post adaptation diagnostics and finalized-memory interventions were evaluated across nine dataset-seed conditions. Writer capability was fully preserved, with 100% post-adaptation accuracy. Cyclic reassignment of finalized matrices produced diagnostic accuracy gaps of 86.3 to 86.9 percentage points, showing strong dependence on example memory correspondence. In contrast, natural text macro F1 changed by less than 0.002 when finalized matrices were reassigned, zeroed, or replaced by batch means. Locked-test macro F1 was 90.94% on AG News, 81.78% on IMDB, and 62.63% on Yelp Review Full, comparable to compact controls. Preserving associative capability and maintaining diagnostic access to sample specific memory did not imply measurable downstream reliance on that memory. Protected memory designs should therefore treat capability preservation, diagnostic access, and task alignment as separate objectives and evaluate downstream memory sensitivity directly.

记忆机制模型诊断文档分类可解释性

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。