datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
KGQASubgraphsRanking
📰 News
[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.
Dataset Summary
KGQASubgraphsRanking is the total-packaged dataset for both publications mentioned in the News section.… See the full description on the dataset page: https://huggingface.co/datasets/s-nlp/KGQASubgraphsRanking.KGQA_T5-xl-ssm
Dataset Card for "KGQA_T5-xl-ssm"
More Information needed
KGQA_Mixtral
Dataset Card for "KGQA_Mixtral"
More Information needed
KGQA_T5-large-ssm
Dataset Card for "KGQA_T5-large-ssm"
More Information needed
KGQA_Mistral
Dataset Card for "KGQA_Mistral"
More Information needed
dynamic_kgqaKORA-Benchmark
KORA Benchmark
Resources for reproducing KORA: Adaptive Multi-Agent Orchestrated Retrieval over Knowledge Graphs — including the BioCQ benchmark dataset, entity resolution indexes, and the combined biomedical knowledge graph.
Repository Contents
Path
Description
benchmark/
BioCQ question splits (train / val / test / full)
indexes/scispacy*/
Pre-built SciSpaCy entity resolution indexes (~1 GB)
indexes/ark_bm25/
Pre-built ARK BM25 retrieval indexes… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-kgqa/KORA-Benchmark.