Recently, large language models (LLMs) have been successful in relational extraction (RE) tasks, especially in the few-shot learning. An important problem in the field of RE is long-tailed data, while not much attention is currently paid to this problem using LLM approaches. Therefore, in this paper, we propose SLCoLM, a model collaboration framework, to mitigate the data long-tail problem. In our framework, We use the ``\textit{Training-Guide-Predict}'' strategy to combine the strengths of pre-trained language models (PLMs) and LLMs, where a task-specific PLM framework acts as a tutor, transfers task knowledge to the LLM, and guides the LLM in performing RE tasks. Our experiments on a RE dataset rich in relation types show that the approach in this paper facilitates RE of long-tail relation types.

翻译：近期，大型语言模型（LLMs）在关系抽取（RE）任务中取得了成功，尤其是在少样本学习场景下。关系抽取领域的一个重要问题是长尾数据问题，然而目前基于LLM的方法对此问题的关注尚不充分。为此，本文提出SLCoLM——一种模型协作框架，旨在缓解数据长尾问题。在该框架中，我们采用“训练-引导-预测”策略，结合预训练语言模型（PLMs）与LLMs的优势：由特定任务的PLM框架充当导师角色，向LLM传递任务知识，并引导LLM执行关系抽取任务。在包含丰富关系类型的关系抽取数据集上的实验表明，本文方法有助于促进长尾关系类型的关系抽取。