List your company

Question Answering on DiaASQ (test)

50LLM-as-a-Judge ScorePersonalAI
10.4820.743141.26Jun 20, 2025

Evaluation results

MethodLinks
PersonalAILLM=GPT4o-mini, Retrieval algorithm=BeamSearch + WaterCircles, Graph restriction=episodic vertices excluded2025.0650
PersonalAILLM=DeepSeek V3, Retrieval algorithm=BeamSearch + WaterCircles, Graph restriction=object vertices excluded2025.0647
PersonalAILLM=Qwen2.5 7B, Retrieval algorithm=BeamSearch, Graph restriction=no restrictions2025.0622
PersonalAILLM=Llama3.1 8B, Retrieval algorithm=BeamSearch, Graph restriction=episodic vertices excluded2025.0619
PersonalAILLM=DeepSeek R1 7B, Retrieval algorithm=A*, Graph restriction=episodic vertices excluded2025.0612