KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Open paper
Benchmark
Model
Rank
Results
question-answering-on-openbookqa
LLM-KGFR (GPT-4o-mini)
–
Accuracy: 90.0
question-answering-on-openbookqa
LLM-KGFR (Qwen-max)
–
Accuracy: 95.6
Rank counts only results with a code link.