Comparison
10 contributions
Exploring LLMs as Enhancer to assist graph-related tasks in literature
Graphs play a crucial role in illustrating and examining complex relationship in practical scenarios, such as citation networks, social networks, and biological data. Currently, Large Language Models (LLMs), highly successful across diverse fields, have been applied to graph-related tasks, surpassing conventional methods based on Graph Neural Networks (GNNs) and achieving cutting-edge performance. This comparison initiates with a thorough examination and analysis of current approaches that combine LLMs with graphs and able to answer different research questions such as:
RQ1: which GNN type is used in the proposed model?
RQ2: which LLM type is used in the proposed model?
RQ3: Datasets used for the evaluation of proposed model?
RQ4: What are the limitations of proposed model?
RQ5: What are the specific domain of model?
Comparison update
ORKG Comparisons have changed. We have added new features and improved the user interface. Comparisons might look slightly different, but the comparison data itself remains unchanged.