The researchers used GPT4Score as a model-based evaluation metric, defined as the percentage of answers that GPT-4o identifies as correct when assessing if the model's output matches the ground truth answer.

Authors

• Person: Not available Organization: arXiv
  Grounding LLM Reasoning with Knowledge Graphs - arXiv

Sources

• Grounding LLM Reasoning with Knowledge Graphs - arXiv arxiv.org arXiv via serper

Referenced by nodes (1)

• GPT-4 concept