Knowledge editing (KE) aims to efficiently and precisely modify the behavior
of large language models (LLMs) to update specific knowledge without negatively
influencing other knowledge. Current research primarily focuses on white-box
LLMs editing, overlooking an important scenario: black-box LLMs editing, where
LLMs are accessed through interfaces and only textual output is available. To
address the limitations of existing evaluations that are not inapplicable to
black-box LLM editing and lack comprehensiveness, we propose a
multi-perspective evaluation framework, incorporating the assessment of style
retention for the first time. To tackle privacy leaks of editing data and style
over-editing in current methods, we introduce a novel postEdit framework,
resolving privacy concerns through downstream post-processing and maintaining
textual style consistency via fine-grained editing to original responses.
Experiments and analysis on two benchmarks demonstrate that postEdit
outperforms all baselines and achieves strong generalization, especially with
huge improvements on style retention (average $+20.82\%\uparrow$).

当前研究主要关注白盒大语言模型（LLMs）编辑，忽略了一个重要的场景：黑盒 LLMs 编辑，其中 LLMs 通过接口进行访问，仅有文本输出可用。为了解决现有评估不适用于黑盒 LLMs 编辑且不具备全面性的局限性，我们提出了一个多角度评估框架，首次加入了风格保留的评估。为了解决当前方法中的编辑数据隐私泄露和过度编辑风格的问题，我们引入了一种新的 postEdit 框架，通过下游后处理解决隐私问题，并通过细粒度编辑保持文本风格一致。两个基准实验和分析表明，postEdit 超过了所有对比基准并实现了强大的泛化性能，特别是在风格保留上获得了巨大的提升（平均提高了 20.82%）。