Factual Consistency Evaluation on QAGS-XSum (test)
5.27Pearson Correlation CoefficientALIGNSCORE-large
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ALIGNSCORE-largeType=Ours2023.05 | 5.27 | — | — | |
| ALIGNSCORE-baseType=Ours2023.05 | 4.95 | — | — | |
| UniEvalType=Misc2023.05 | 4.55 | — | — | |
| QAFactEvalType=QA2023.05 | 4.42 | — | — | |
| SummaC-ZSType=NLI2023.05 | 4.37 | — | — | |
| DAEType=NLI2023.05 | 3.75 | — | — | |
| SummaC-CONVType=NLI2023.05 | 3.64 | — | — | |
| NER-OverlapType=Similarity Matching2023.05 | 3.12 | — | — | |
| CTCType=Misc2023.05 | 3.06 | — | — | |
| FactCCType=Misc2023.05 | 2.88 | — | — | |
| BARTScoreType=Misc2023.05 | 1.63 | — | — | |
| ROUGE-1Type=Similarity Matching2023.05 | 1.57 | — | — | |
| ROUGE-2Type=Similarity Matching2023.05 | 1.44 | — | — | |
| BLEURTType=Regression2023.05 | 1.32 | — | — | |
| ROUGE-LType=Similarity Matching2023.05 | 1.25 | — | — | |
| SimCSEType=Similarity Matching2023.05 | 1.19 | — | — | |
| QuestEvalType=QA2023.05 | 1.17 | — | — | |
| BLEUType=Similarity Matching2023.05 | 1.09 | — | — | |
| MNLIType=NLI2023.05 | 0.61 | — | — | |
| G-EvalBackbone=GPT-42026.06 | 0.558 | 0.537 | 0.472 | |
| BINEVALBackbone=Claude2026.06 | 0.543 | 0.539 | 0.47 | |
| UniEvalBackbone=gpt-oss2026.06 | 0.49 | 0.49 | 0.49 | |
| UniEvalBackbone=T52026.06 | 0.461 | 0.488 | 0.399 | |
| BINEVALBackbone=gpt-oss2026.06 | 0.435 | 0.483 | 0.433 | |
| CTC2026.06 | 0.309 | 0.295 | 0.242 | |
| FactCC2026.06 | 0.297 | 0.259 | 0.212 | |
| G-EvalBackbone=gpt-oss2026.06 | 0.236 | 0.236 | 0.236 | |
| BARTScore2026.06 | 0.184 | 0.159 | 0.13 | |
| BLANCType=Misc2023.05 | 0.18 | — | — | |
| QAGS2026.06 | 0.175 | — | — | |
| MoverScore2026.06 | 0.054 | 0.044 | 0.036 | |
| ROUGE-L2026.06 | 0.024 | -0.011 | -0.009 | |
| BERTScore2026.06 | 0.024 | 0.008 | 0.006 | |
| FEQAType=QA2023.05 | -0.73 | — | — | |
| BERTScoreType=Similarity Matching2023.05 | -1.06 | — | — |