可检索梯度：无累积权重漂移的持续后训练
Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift
AI总结：
提出ReGrad范式，将梯度作为可检索知识单元，通过元学习重塑文档梯度为通用适应信号，实现无权重漂移的可扩展参数知识注入。
摘要：
持续后训练使模型在部署后能够吸收新知识，但重复更新共享参数会累积权重漂移，可能导致灾难性遗忘并降低通用能力。检索增强生成避免了这种参数漂移，但往往缺乏参数化知识整合的深度。在本文中，我们提出ReGrad（可检索梯度），一种将梯度视为可检索知识单元的新范式。ReGrad离线预计算文档特定梯度，存储在索引化的梯度库中，并在推理时仅检索与查询相关的梯度以进行临时权重调整。然而，原始语言建模梯度针对词级文档重建而非查询驱动的知识使用进行优化。因此，我们引入双层元学习目标，将文档派生梯度重塑为下游任务的通用适应信号。在通用和特定领域设置上的实验表明，ReGrad优于CPT和RAG基线，实现了可扩展且可逆的参数知识注入，且不累积权重漂移。
英文摘要：
Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing catastrophic forgetting and degrading general capabilities. Retrieval-augmented generation avoids such parameter drift, yet often lacks the depth of parametric knowledge integration. In this paper, we propose ReGrad (Retrievable Gradients), a new paradigm that treats gradients as retrievable units of knowledge. ReGrad pre-computes document-specific gradients offline, stores them in an indexed Gradient Bank, and retrieves only query-relevant gradients at inference time for temporary weight adaptation. However, raw language-modeling gradients are optimized for token-level document reconstruction rather than for query-driven knowledge use. We therefore introduce a bi-level meta-learning objective that reshapes document-derived gradients into generalizable adaptation signals for downstream tasks. Experiments across general and domain-specific settings show that \textsc{ReGrad} outperforms CPT and RAG baselines, enabling scalable and reversible parametric knowledge injection without accumulating weight drift.
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。
