The substantial interest in updating Large Language Models (LLMs) without retraining from scratch is accompanied by several challenges. This is particularly true when updating LLMs with datasets that necessitate domain-expert reasoning across extensive texts, despite limited samples. We termed the scenario as the Few-Shot Domain-Expert Reasoning for Updating LLMs (FDoR-UL). Traditional methods such as Low-Rank Adaptation (LoRA) and Retrieval Augmented Generation (RAG) are inadequate for addressing this critical issue, particularly evident in our exploration of a specific medical dataset that epitomizes the distinct needs of FDoR-UL. To tackle this challenge, we introduce a Sequential Fusion method to integrate knowledge from complex contexts into LLMs. This method employs a two-stage framework: initially leveraging general LLMs to perform relation extraction for knowledge acquisition from complex texts, followed by updating domain-specific LLMs through Knowledge Editing (KE). Employing our method, domain-specific LLMs achieved a 71.7% accuracy (an average gain of 39.1%) in question-answering tasks. Furthermore, we expanded our evaluation to a novel economics-management dataset we developed, where our method achieved a 75.0% accuracy (an average gain of 45.0%). These findings underscore the effectiveness and flexibility of our approach in FDoR-UL across various domains.

翻译：在不从头开始重新训练的情况下更新大型语言模型（LLMs）引起了广泛关注，同时也伴随着诸多挑战。当使用需要在有限样本下对长文本进行领域专家推理的数据集来更新LLMs时，这一挑战尤为突出。我们将此场景定义为面向LLM更新的少样本领域专家推理（FDoR-UL）。传统方法如低秩适应（LoRA）和检索增强生成（RAG）难以有效解决这一关键问题，这一点在我们对一个具体医疗数据集的探索中尤为明显，该数据集集中体现了FDoR-UL的独特需求。为应对这一挑战，我们提出了一种序列融合方法，将复杂上下文中的知识整合到LLMs中。该方法采用两阶段框架：首先利用通用LLMs从复杂文本中执行关系抽取以获取知识，随后通过知识编辑（KE）来更新领域特定的LLMs。应用我们的方法后，领域特定LLMs在问答任务中达到了71.7%的准确率（平均提升39.1%）。此外，我们将评估扩展到一个我们新开发的经济管理数据集，在该数据集上我们的方法取得了75.0%的准确率（平均提升45.0%）。这些发现凸显了我们的方法在跨不同领域的FDoR-UL场景中的有效性和灵活性。