让大模型精准修改事实，避免整体记忆偏差
FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing
- 分步编辑：先锚定细粒度事实，再微调深层生成
- 在问答任务中准确率提升显著，同时保持整体生成质量
- 适合需要精确知识更新的研究者和应用开发
无结构模型编辑旨在用真实文本更新模型，但现有方法常整体记忆文本，缺乏可靠的细粒度事实访问能力。为此，我们提出FABLE，一种分层框架，将细粒度事实注入与整体文本生成解耦。FABLE采用两阶段、以事实为先的策略：在浅层锚定离散事实，再对深层进行最小化更新以生成连贯文本。这种解耦解决了整体回忆与细粒度事实访问之间的不匹配问题，契合Transformer单向流动特性——表层生成会放大而非修正底层事实表示。我们还引入UnFine，一个包含细粒度问答对和事实级评估指标的诊断基准。实验表明，FABLE在细粒度问答上表现显著提升，同时维持了最先进的整体编辑性能。代码已公开于https://github.com/caskcsg/FABLE。
原文摘要 · Abstract (English)
Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grained fact access. To address this, we propose FABLE, a hierarchical framework that decouples fine-grained fact injection from holistic text generation. FABLE follows a two-stage, fact-first strategy: discrete facts are anchored in shallow layers, followed by minimal updates to deeper layers to produce coherent text. This decoupling resolves the mismatch between holistic recall and fine-grained fact access, reflecting the unidirectional Transformer flow in which surface-form generation amplifies rather than corrects underlying fact representations. We also introduce UnFine, a diagnostic benchmark with fine-grained question-answer pairs and fact-level metrics for systematic evaluation. Experiments show that FABLE substantially improves fine-grained question answering while maintaining state-of-the-art holistic editing performance. Our code is publicly available at https://github.com/caskcsg/FABLE.
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。