[12/2023] Publishing of the original paper "Large Language Models Meets Knowledge Graph to Answer Factoid Questions". This paper first introduces the novelty of the extracted subgraphs; which provide valuable information for different methods of ranking. The paper leveraged T5-like models, and achieve SOTA results with Graph2Text ranking.
KGQASubgraphsRanking is the total-packaged dataset for both publications mentioned in the News section.ā¦ See the full description on the dataset page:
https://huggingface.co/datasets/s-nlp/KGQASubgraphsRanking.
