Question Answering on TriviaQA (test) (LLM-as-a-Judge)
0.87LLM Judge ScorePersonalAI
Evaluation results
| Method | Links | |
|---|---|---|
| PersonalAILLM=DeepSeek V3, Retrieval algorithm=BeamSearch + WaterCircles, Graph restriction=no restrictions2025.06 | 0.87 | |
| PersonalAILLM=Llama3.1 8B, Retrieval algorithm=BeamSearch + A*, Graph restriction=episodic vertices excluded2025.06 | 0.66 | |
| PersonalAILLM=Qwen2.5 7B, Retrieval algorithm=BeamSearch, Graph restriction=episodic vertices excluded2025.06 | 0.34 | |
| PersonalAILLM=DeepSeek R1 7B, Retrieval algorithm=A*, Graph restriction=episodic vertices excluded2025.06 | 0.27 |