Knowledge Graph Question Answering on QALD-9 Wikidata (test)
79.4Exact Match AccuracySoG
Evaluation Results
| Method | Links | |
|---|---|---|
| SoGBackbone=GPT-4o2025.10 | 79.4 | |
| IO PromptBackbone=GPT-4o2025.10 | 66.7 | |
| Chain-of-ThoughtBackbone=GPT-4o2025.10 | 65.1 | |
| Self-ConsistencyBackbone=GPT-4o2025.10 | 63.5 | |
| Think-on-GraphBackbone=GPT-4o, Reproduced status=reproduced2025.10 | 58.9 | |
| SpinachBackbone=GPT-4o2025.10 | 58.3 |