Summary of Llm As Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge Graphs, by Kai Wang et al.
LLM as Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge Graphs
by Kai Wang, Yuwei Xu, Zhiyong Wu, Siqiang Luo
First submitted to arxiv on: 19 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed paper addresses the challenge of knowledge graph (KG) inductive reasoning in low-resource scenarios, where there is a scarcity of both textual and structural aspects. To tackle this issue, Large Language Models (LLMs) are utilized to generate a graph-structural prompt that enhances pre-trained Graph Neural Networks (GNNs). This approach brings new methodological insights into KG inductive reasoning methods and high generalizability in practice. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a novel pretraining and prompting framework called ProLINK, designed for low-resource inductive reasoning across arbitrary KGs without requiring additional training. ProLINK is experimentally evaluated on 36 low-resource KG datasets and outperforms previous methods in three-shot, one-shot, and zero-shot reasoning tasks, with average performance improvements of 20%, 45%, and 147% respectively. |
Keywords
» Artificial intelligence » Knowledge graph » One shot » Pretraining » Prompt » Prompting » Zero shot
