Model editing techniques modify a minor proportion of knowledge in Large Language Models (LLMs) at a relatively low cost, which have demonstrated notable success. Existing methods assume Transformer Layer (TL) hidden states are values of key-value memories of the Feed-Forward Network (FFN). They usually optimize the TL hidden states to memorize target knowledge and use it to update the weights of the FFN in LLMs. However, the information flow of TL hidden states comes from three parts: Multi-Head Self-Attention (MHSA), FFN, and residual connections. Existing methods neglect the fact that the TL hidden states contains information not specifically required for FFN. Consequently, the performance of model editing decreases. To achieve more precise model editing, we analyze hidden states of MHSA and FFN, finding that MHSA encodes certain general knowledge extraction patterns. This implies that MHSA weights do not require updating when new knowledge is introduced. Based on above findings, we introduce PMET, which simultaneously optimizes Transformer Component (TC, namely MHSA and FFN) hidden states, while only using the optimized TC hidden states of FFN to precisely update FFN weights. Our experiments demonstrate that PMET exhibits state-of-the-art performance on both the COUNTERFACT and zsRE datasets. Our ablation experiments substantiate the effectiveness of our enhancements, further reinforcing the finding that the MHSA encodes certain general knowledge extraction patterns and indicating its storage of a small amount of factual knowledge. Our code is available at https://github.com/xpq-tech/PMET.

翻译：模型编辑技术能够以相对较低的成本修改大型语言模型（LLMs）中的少量知识，并已展现出显著成效。现有方法将Transformer层（TL）的隐藏状态视为前馈网络（FFN）键值记忆的值。它们通常优化TL隐藏状态以记忆目标知识，并利用其更新LLM中FFN的权重。然而，TL隐藏状态的信息流包含三部分：多头自注意力（MHSA）、FFN和残差连接。现有方法忽略了TL隐藏状态包含并非FFN特需的信息，从而导致模型编辑性能下降。为实现更精确的模型编辑，我们分析了MHSA和FFN的隐藏状态，发现MHSA编码了某些通用知识提取模式。这意味着在新知识引入时无需更新MHSA权重。基于上述发现，我们提出PMET，它同时优化Transformer组件（TC，即MHSA和FFN）的隐藏状态，但仅使用FFN的优化后TC隐藏状态精确更新FFN权重。实验表明，PMET在COUNTERFACT和zsRE数据集上均达到最先进性能。消融实验证实了我们改进的有效性，进一步验证了MHSA编码通用知识提取模式的发现，并表明其存储了少量事实性知识。我们的代码开源在https://github.com/xpq-tech/PMET。