通过思维链进行知识编辑
Knowledge Editing through Chain-of-Thought
AI总结：
本文提出EditCoT框架，通过生成并迭代优化思维链来更新大语言模型知识，无需重新训练，在多种语言和任务基准上达到最先进性能，兼具泛化性、有效性和稳定性。
摘要：
知识编辑是一种利用新信息更新大型语言模型（LLMs）以维持其世界知识的技术。这种方法避免了从头重建模型的需要，从而解决了频繁重新训练所带来的高成本问题。其中，上下文内编辑范式因其在整合新知识的同时保持模型原有能力方面的有效性而脱颖而出。尽管具有潜力，现有的上下文内知识编辑方法通常是针对特定任务的，主要利用结构化知识三元组专注于多跳问答任务。此外，它们依赖少样本提示进行任务分解，这使得它们在不同任务间的泛化上不稳定且效果较差。针对这些局限性，我们提出了EditCoT，一种新颖的知识编辑框架，能够灵活高效地在各种任务上更新LLMs而无需重新训练。EditCoT通过为给定输入生成思维链（CoT），然后利用基于更新知识的CoT编辑器迭代地优化这一CoT过程来工作。我们在涵盖多种语言和任务的多样化基准上评估了EditCoT。结果表明，与现有方法相比，我们的方法在实现最先进性能的同时，提供了更优越的泛化能力、有效性和稳定性，标志着知识更新领域的重大进步。EditCoT的代码和数据可在https://github.com/bebr2/EditCoT获取。
英文摘要：
Knowledge Editing is a technique that updates large language models (LLMs) with new information to maintain their world knowledge. This approach avoids the need to rebuild the model from scratch, thereby addressing the high costs associated with frequent retraining. Among these, the in-context editing paradigm stands out for its effectiveness in integrating new knowledge while preserving the model's original capabilities. Despite its potential, existing in-context knowledge editing methods are often task-specific, focusing primarily on multi-hop QA tasks using structured knowledge triples. Moreover, their reliance on few-shot prompting for task decomposition makes them unstable and less effective in generalizing across diverse tasks. In response to these limitations, we propose EditCoT, a novel knowledge editing framework that flexibly and efficiently updates LLMs across various tasks without retraining. EditCoT works by generating a chain-of-thought (CoT) for a given input and then iteratively refining this CoT process using a CoT editor based on updated knowledge. We evaluate EditCoT across a diverse range of benchmarks, covering multiple languages and tasks. The results demonstrate that our approach achieves state-of-the-art performance while offering superior generalization, effectiveness, and stability compared to existing methods, marking a significant advancement in the field of knowledge updating. The code and data of EditCoT are available at: https://github.com/bebr2/EditCoT .
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。
