HPSE：通过混合策略自编辑实现可组合非结构化知识编辑

AI 摘要

HPSE是一种用于非结构化知识编辑的新方法，通过从混合轨迹中蒸馏来将缺失事实插入模型的推理路径，从而实现可组合的多跳推理。该方法解决了现有编辑器无法利用注入段落的问题，并在四个LLM骨干和两个KE编辑器上展示了即插即用的改进。

正文节选

Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing Abstract HPSE improves unstructured knowledge editing by distilling from hybrid rollouts that insert missing facts into the model's reasoning paths, enabling composable multi-hop reasoning. Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge quickly becomes outdated in a fast-changing world. This motivates knowledge editing (KE

发布时间：—

抓取时间：2026-08-14 23:19

来源机构：Hugging Face