用知识编码本解决大模型更新中的删改冲突问题
Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating
- 构建多记忆体知识编码本，按相似性分组存储新知识
- 通过冲突评分机制分离编辑与删减任务，避免相互干扰
- 适合需要频繁更新知识的大模型应用开发者
大型语言模型（LLMs）在自然语言处理中表现优异，依赖于持续的知识更新。更新过程需同时完成删去旧知识和添加新知识两项任务，现有方法面临知识存储效率低（过稀疏或过密集）以及删改任务冲突的问题。为此，我们提出LOKA框架，基于知识编码本实现无冲突的模型更新。训练阶段，新知识被存入多个编码本记忆体；通过相似性感知映射，将相关知识聚类至同一记忆体。为缓解任务冲突，采用基于冲突评分的任务特异性和多任务记忆体设计。推理阶段，系统从编码本中检索最相关记忆体，并注入原模型以应用更新知识。学习型路由器控制编码本激活，提升知识利用效率。大量实验验证了LOKA在知识更新任务中的有效性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel in natural language processing by encoding extensive human knowledge, but their utility relies on timely updates as knowledge evolves. Updating LLMs involves two key tasks simultaneously: unlearning to remove unwanted knowledge and editing to incorporate new information. Existing methods face two major challenges: ineffective knowledge storage (either too sparse or too dense) and task conflicts between editing and unlearning, as validated through our theoretical and experimental results. To address these issues, we propose LOKA, a conflict-free framework for LLM updating based on a knowledge codebook. During training, updated knowledge is stored in multiple codebook memories. To optimize knowledge storage, a similarity-aware knowledge mapping ensures that related knowledge pieces are clustered and allocated to the same memory. Additionally, LOKA resolves task conflicts by employing task-specific and multi-task memories guided by a conflict score. In the inference stage, LOKA retrieves the most relevant memory from the codebook and plugs it into the original LLM to apply the updated knowledge. A learning-based router controls codebook activation to further improve knowledge utilization. Extensive experiments demonstrate the effectiveness of LOKA in LLM knowledge updating tasks.
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。