检索增强的多语言知识编辑
Retrieval-augmented Multilingual Knowledge Editing
AI总结：
针对多语言知识编辑问题，提出检索增强的多语言知识编辑器ReMaKE，通过拼接检索的新知识与提示实现模型无关编辑，显著优于基线，并提供12种语言数据集。
摘要：
大型语言模型（LLMs）中表示的知识常常是不正确的，并且也可能随着时间的推移而过时。通过微调来更新知识在计算上耗费资源且不可靠，因此知识编辑（KE）已发展成为一种有效且经济的替代方案，用于向LLMs注入新知识或修正事实错误。尽管该领域引起了相当大的关注，但当前的知识编辑研究仅专注于单语言环境，通常是英语。然而，如果新知识以某种语言提供，而我们希望用另一种语言查询LLM，会发生什么？为了解决多语言知识编辑的问题，我们提出了检索增强的多语言知识编辑器（ReMaKE），用于更新LLMs中的新知识。ReMaKE能够在多语言环境中执行与模型无关的知识编辑。ReMaKE将从多语言知识库中检索到的新知识与提示词拼接在一起。我们的实验结果表明，ReMaKE显著优于基线知识编辑方法，并且是首个在多语言环境中工作的知识编辑方法。我们提供了包含12种语言的多语言知识编辑数据集（MzsRE），该数据集以及代码和更多项目信息可在https://github.com/Vicky-Wil/ReMaKE获取。
英文摘要：
Knowledge represented in Large Language Models (LLMs) is quite often incorrect and can also become obsolete over time. Updating knowledge via fine-tuning is computationally resource-hungry and not reliable, and so knowledge editing (KE) has developed as an effective and economical alternative to inject new knowledge or to fix factual errors in LLMs. Although there has been considerable interest in this area, current KE research exclusively focuses on the monolingual setting, typically in English. However, what happens if the new knowledge is supplied in one language, but we would like to query the LLM in a different language? To address the problem of multilingual knowledge editing, we propose Retrieval-augmented Multilingual Knowledge Editor (ReMaKE) to update new knowledge in LLMs. ReMaKE can perform model-agnostic knowledge editing in multilingual settings. ReMaKE concatenates the new knowledge retrieved from a multilingual knowledge base with prompts. Our experimental results show that ReMaKE outperforms baseline knowledge editing methods by a significant margin and is the first KE method to work in a multilingual setting. We provide our multilingual knowledge editing dataset (MzsRE) in 12 languages, which along with code, and additional project information is available at https://github.com/Vicky-Wil/ReMaKE.
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。
