Zero- and Few-Shots Knowledge Graph Triplet Extraction with Large Language Models
This work addresses knowledge graph construction for AI applications, but it is incremental as it applies existing LLM methods to a specific task with contextual enhancements.
The paper tackled knowledge graph triplet extraction by testing large language models in zero- and few-shot settings, using a pipeline that dynamically gathers contextual information from a knowledge base to improve performance, making LLMs competitive with older fully trained baselines like BiLSTM networks.
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.