In this work, we tested the Triplet Extraction (TE) capabilities of a variety of Large Language Models (LLMs) of different sizes in the Zero- and Few-Shots settings. In detail, we proposed a pipeline that dynamically gathers contextual information from a Knowledge Base (KB), both in the form of context triplets and of (sentence, triplets) pairs as examples, and provides it to the LLM through a prompt. The additional context allowed the LLMs to be competitive with all the older fully trained baselines based on the Bidirectional Long Short-Term Memory (BiLSTM) Network architecture. We further conducted a detailed analysis of the quality of the gathered KB context, finding it to be strongly correlated with the final TE performance of the model. In contrast, the size of the model appeared to only logarithmically improve the TE capabilities of the LLMs.

翻译：本研究在零样本与少样本设定下，测试了不同规模的大语言模型（LLMs）在三元组抽取（TE）任务中的能力。具体而言，我们提出了一种流水线方法，通过从知识库（KB）中动态收集上下文信息（包括上下文三元组形式及（句子，三元组）配对示例），并通过提示词将其提供给大语言模型。额外上下文使大语言模型能够与所有基于双向长短期记忆（BiLSTM）网络架构的早期全训练基线模型相媲美。进一步地，我们对所收集知识库上下文的质量进行了详细分析，发现其与模型的三元组抽取最终表现呈强相关性。相比之下，模型规模对三元组抽取能力的提升仅呈对数级增长。