Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Semantic Consistency Evaluation on DSG

84.3Average Answering Accuracy

VisualPrompter

46.44456.27266.175.928Jun 29, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.06
84.383
2025.06
82.683
2025.06
81.774.6
2025.06
79.578.4
2025.06
79.178.4
2025.06
7876.2
2025.06
7783
2025.06
76.976.2
2025.06
75.574.6
2025.06
72.178.4
2025.06
69.583
2025.06
68.774.6
2025.06
68.776.2
2025.06
67.578.4
2025.06
65.176.2
2025.06
58.474.6
2025.06
55.353.5
2025.06
51.553.5
2025.06
49.653.5
2025.06
47.953.5