Neural language models (LMs) have been extensively trained on vast corpora to
store factual knowledge about various aspects of the world described in texts.
Current technologies typically employ knowledge editing methods or specific
prompts to modify LM outputs. However, existing knowledge editing methods are
costly and inefficient, struggling to produce appropriate text. Additionally,
prompt engineering is opaque and requires significant effort to find suitable
prompts. To address these issues, we introduce a new method called PSPEM
(Prefix Soft Prompt Editing Method), that can be used for a lifetime with just
one training. It resolves the inefficiencies and generalizability issues in
knowledge editing methods and overcomes the opacity of prompt engineering by
automatically seeking optimal soft prompts. Specifically, PSPEM utilizes a
prompt encoder and an encoding converter to refine key information in prompts
and uses prompt alignment techniques to guide model generation, ensuring text
consistency and adherence to the intended structure and content, thereby
maintaining an optimal balance between efficiency and accuracy. We have
validated the effectiveness of PSPEM through knowledge editing and attribute
inserting. On the COUNTERFACT dataset, PSPEM achieved nearly 100\% editing
accuracy and demonstrated the highest level of fluency. We further analyzed the
similarities between PSPEM and original prompts and their impact on the model's
internals. The results indicate that PSPEM can serve as an alternative to
original prompts, supporting the model in effective editing.

我们介绍了一种名为 PSPEM 的新方法，它可以解决知识编辑方法的低效性和通用性问题，通过自动寻找最佳软提示来克服提示工程的不透明性，从而在效率和准确性之间保持最佳平衡。我们通过知识编辑和属性插入验证了 PSPEM 的有效性，在 COUNTERFACT 数据集上实现了近 100％的编辑准确性，并展示了最高水平的流畅性。

通过重述前缀提示编辑语言模型的知识表示

Editing Knowledge Representation of Language Lodel via Rephrased Prefix  Prompts

Knowledge editing aims to inject knowledge updates into language models to
keep them correct and up-to-date. However, its current evaluation strategies
are notably impractical: they solely update with well-curated structured facts
(triplets with subjects, relations, and objects), whereas real-world knowledge
updates commonly emerge in unstructured texts like news articles. In this
paper, we propose a new benchmark, Unstructured Knowledge Editing (UKE). It
evaluates editing performance directly using unstructured texts as knowledge
updates, termed unstructured facts. Hence UKE avoids the laborious construction
of structured facts and enables efficient and responsive knowledge editing,
becoming a more practical benchmark. We conduct extensive experiments on newly
built datasets and demonstrate that UKE poses a significant challenge to
state-of-the-art knowledge editing methods, resulting in their critical
performance declines. We further show that this challenge persists even if we
extract triplets as structured facts. Our analysis discloses key insights to
motivate future research in UKE for more practical knowledge editing.

知识编辑目标是将知识更新注入语言模型中以保持其正确性和最新性。然而，当前的评估策略明显不实用：它们仅以精心策划的结构化事实（包含主语、关系和宾语的三元组）进行更新，而真实世界的知识更新通常出现在无结构的文本中，如新闻文章。本文提出一个新的基准，无结构知识编辑（Unstructured Knowledge Editing，简称 UKE），直接使用无结构的文本作为知识更新进行编辑性能评估，从而避免了繁琐的结构化事实构建，并实现了高效和响应性的知识编辑，成为一个更实用的基准。我们在新构建的数据集上进行了广泛的实验，并证明 UKE 对于最先进的知识编辑方法构成了重大挑战，导致它们的性能显著下降。我们进一步展示，即使将三元组提取为结构化事实，这个挑战仍然存在。我们的分析揭示了激励未来 UKE 研究的关键见解，以实现更实用的知识编辑。

使用非结构化事实更新语言模型：实现实用的知识编辑

Updating Language Models with Unstructured Facts: Towards Practical  Knowledge Editing

Knowledge editing aims to change language models' performance on several
special cases (i.e., editing scope) by infusing the corresponding expected
knowledge into them. With the recent advancements in large language models
(LLMs), knowledge editing has been shown as a promising technique to adapt LLMs
to new knowledge without retraining from scratch. However, most of the previous
studies neglect the multi-lingual nature of some main-stream LLMs (e.g., LLaMA,
ChatGPT and GPT-4), and typically focus on monolingual scenarios, where LLMs
are edited and evaluated in the same language. As a result, it is still unknown
the effect of source language editing on a different target language. In this
paper, we aim to figure out this cross-lingual effect in knowledge editing.
Specifically, we first collect a large-scale cross-lingual synthetic dataset by
translating ZsRE from English to Chinese. Then, we conduct English editing on
various knowledge editing methods covering different paradigms, and evaluate
their performance in Chinese, and vice versa. To give deeper analyses of the
cross-lingual effect, the evaluation includes four aspects, i.e., reliability,
generality, locality and portability. Furthermore, we analyze the inconsistent
behaviors of the edited models and discuss their specific challenges.

本文旨在研究知识编辑领域中源语言编辑对不同目标语言的交叉效应，通过将 ZsRE 从英文翻译成中文，构建大规模的跨语言合成数据集，对不同范式的知识编辑方法进行英文和中文的编辑，并评估其在不同方面的性能。进一步分析编辑模型的不一致行为并讨论其挑战。