解决大模型多跳问答中知识编辑跳过问题，提升准确性
Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
- 通过引导分解，逐步检索并整合编辑后的知识
- 在多跳问答中准确率提升，显著减少知识跳过现象
- 适合需要频繁更新知识的问答系统开发者
在信息快速更新的世界中，大型语言模型（LLMs）的知识容易过时。重新训练成本过高，因此无需修改参数的知识编辑（KE）尤为必要。我们发现，尽管现有基于检索增强生成（RAG）的KE方法在简单知识编辑上表现良好，但在多跳问答中因‘编辑跳过’问题而失效——即推理时跳过了相关已编辑事实。这一问题不仅源于自然语言表达的多样性，还源于模型解决问题的粒度与编辑记忆中事实粒度不匹配。为此，我们提出一种新的迭代式检索增强知识编辑方法（IRAKE），通过单个编辑事实和完整编辑案例的双重引导，实现精准知识整合。实验表明，IRAKE有效缓解了因编辑跳过导致的失败，在多跳问答任务中优于当前最先进方法。
原文摘要 · Abstract (English)
In a rapidly evolving world where information updates swiftly, knowledge in large language models (LLMs) becomes outdated quickly. Retraining LLMs is not a cost-effective option, making knowledge editing (KE) without modifying parameters particularly necessary. We find that although existing retrieval-augmented generation (RAG)-based KE methods excel at editing simple knowledge, they struggle with KE in multi-hop question answering due to the issue of "edit skipping", which refers to skipping the relevant edited fact in inference. In addition to the diversity of natural language expressions of knowledge, edit skipping also arises from the mismatch between the granularity of LLMs in problem-solving and the facts in the edited memory. To address this issue, we propose a novel Iterative Retrieval-Augmented Knowledge Editing method with guided decomposition (IRAKE) through the guidance from single edited facts and entire edited cases. Experimental results demonstrate that IRAKE mitigates the failure of editing caused by edit skipping and outperforms state-of-the-art methods for KE in multi-hop question answering.
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。