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

Factual Consistency Evaluation on QAGS-XSum (test)

5.27Pearson Correlation Coefficient

ALIGNSCORE-large

-1.31320.39592.1053.8141May 26, 2023Nov 29, 2023Jun 4, 2024Dec 9, 2024Jun 14, 2025Dec 19, 2025Jun 25, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2023.05
5.27--
2023.05
4.95--
2023.05
4.55--
2023.05
4.42--
2023.05
4.37--
2023.05
3.75--
2023.05
3.64--
2023.05
3.12--
2023.05
3.06--
2023.05
2.88--
2023.05
1.63--
2023.05
1.57--
2023.05
1.44--
2023.05
1.32--
2023.05
1.25--
2023.05
1.19--
2023.05
1.17--
2023.05
1.09--
2023.05
0.61--
2026.06
0.5580.5370.472
2026.06
0.5430.5390.47
2026.06
0.490.490.49
2026.06
0.4610.4880.399
2026.06
0.4350.4830.433
2026.06
0.3090.2950.242
2026.06
0.2970.2590.212
2026.06
0.2360.2360.236
2026.06
0.1840.1590.13
2023.05
0.18--
2026.06
0.175--
2026.06
0.0540.0440.036
2026.06
0.024-0.011-0.009
2026.06
0.0240.0080.006
2023.05
-0.73--
2023.05
-1.06--