DSCA: 动态子空间概念对齐用于终身视觉语言模型编辑
DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing
AI总结：
DSCA通过动态子空间对齐技术，在视觉语言模型中实现精准非干扰编辑，提升终身学习的稳定性与知识保留能力。
摘要：
模型编辑旨在在不重新训练的情况下更新知识以添加新概念和改变相关信息。终身编辑是一项具有挑战性的任务，容易破坏之前学习的概念，尤其是对于视觉语言模型（VLMs）而言，因为连续的编辑可能导致推理退化和跨模态对齐问题。现有的基于门控适配器、激活编辑和参数合并技术的VLM知识编辑方法解决了全微调中出现的灾难性遗忘问题；然而，它们仍然在VLM的共享表示空间中操作，其中概念相互交织，因此编辑会干扰其他不相关概念。我们假设这种不稳定性持续存在，因为当前方法通过优化算法控制编辑，而不是在结构上分离知识。我们引入了动态子空间概念对齐（DSCA），通过设计减轻这一限制，通过将表示空间分解为一组正交的语义子空间，并仅在这些转换空间中提出编辑。这些子空间通过联合视觉语言表示的增量聚类和PCA获得。此过程结构上隔离了概念，使通过将软训练目标的隔离转化为架构属性，从而实现精确的非干扰编辑。手术编辑由多术语损失函数引导，以保持任务保真度、编辑局部性和跨模态对齐。在基础模型冻结的情况下，我们的方法实现了98%的单次编辑成功率，在1000次连续编辑后仍保持超过95%，将幻觉降低3到5个百分点，并在连续指令微调基准上实现了最佳的反向转移（BWT）得分。广泛的实验表明，DSCA在各种数据集和基准上实现了最先进的稳定性与知识保留能力。
英文摘要：
Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, prone to disrupting previously learned concepts, especially for Vision Language Models (VLMs), because sequential edits can lead to degraded reasoning and cross modal misalignment. Existing VLM knowledge editing methods based on gated adapters, activation edits, and parameter merging techniques address catastrophic forgetting seen in full fine tuning; however, they still operate in the shared representation space of the VLM, where concepts are entangled, so edits interfere with other non relevant concepts. We hypothesize that this instability persists because current methods algorithmically control edits via optimization rather than structurally separating knowledge. We introduce Dynamic Subspace Concept Alignment (DSCA) which by design mitigates this limitation by decomposing the representation space into a set of orthogonal semantic subspaces and proposing edits only in those transformed spaces. These subspaces are obtained through incremental clustering and PCA on joint vision language representations. This process structurally isolates concepts, enabling precise, non interfering edits by turning isolation from a soft training objective into an architectural property. The surgical edits are guided by a multi term loss function for maintaining task fidelity, edit locality, and cross modal alignment. With the base model frozen, our method achieves 98 percent single edit success, remains over 95 percent after 1000 sequential edits, lowers hallucination by 3 to 5 percent, and achieves the best backward transfer (BWT) scores on continual instruction tuning benchmarks. Extensive experiments demonstrate DSCA state of the art stability and knowledge retention capability in continual lifelong editing across various datasets and benchmarks.
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。
