Data-to-text evaluation on SFRES
0.389Spearman CorrelationHD-EVAL-NN
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| HD-EVAL-NNIterative alignment training data percentage=50%, Aggregator type=NN2024.02 | 0.389 | — | — | 0.47 | |
| HD-EVAL-NNIterative alignment training data percentage=25%, Aggregator type=NN2024.02 | 0.363 | — | — | 0.453 | |
| UNIEVAL2024.02 | 0.354 | — | — | 0.381 | |
| GPT-4 EVAL2024.02 | 0.347 | — | — | 0.414 | |
| DecompEvalType=Instruction-tuned PLM (Zero-shot)2023.07 | 0.293 | — | — | — | |
| UniEval (Summ)Training Dataset=SummEval2023.07 | 0.279 | — | — | — | |
| DIFFSCORE-FT2026.05 | 0.256 | 0.322 | 0.354 | — | |
| BARTSCORE2024.02 | 0.255 | — | — | 0.28 | |
| G-Eval2026.05 | 0.247 | 0.292 | 0.266 | — | |
| UniEval (Dial)Training Dataset=Topical-Chat2023.07 | 0.243 | — | — | — | |
| BARTSCORE-PROMPTFine-tuning=CNN/DM + Paraphrase, Prompt combination=true2021.06 | 0.238 | — | — | — | |
| BARTScore2026.05 | 0.203 | 0.27 | 0.201 | — | |
| DIFFSCORE2026.05 | 0.194 | 0.224 | 0.303 | — | |
| UniEval2026.05 | 0.192 | 0.216 | 0.246 | — | |
| BARTSCORE-CNNFine-tuning=CNN/DM2021.06 | 0.191 | — | — | — | |
| BARTSCORE-CNN-PARAFine-tuning=CNN/DM + Paraphrase2021.06 | 0.185 | — | — | — | |
| GPTScore2026.05 | 0.178 | 0.213 | 0.237 | — | |
| BARTSCOREFine-tuning=none2021.06 | 0.164 | — | — | — | |
| BERTScore2021.06 | 0.156 | — | — | — | |
| PRISM2021.06 | 0.155 | — | — | — | |
| MoverScore2021.06 | 0.153 | — | — | — | |
| BERTSCORE2024.02 | 0.145 | — | — | 0.164 | |
| BERTScore2026.05 | 0.142 | 0.205 | 0.154 | — | |
| PRISM2024.02 | 0.126 | — | — | 0.146 | |
| ROUGE-22021.06 | 0.116 | — | — | — | |
| ROUGE-12021.06 | 0.115 | — | — | — | |
| ROUGE-L2021.06 | 0.103 | — | — | — | |
| ROUGE-12024.02 | 0.092 | — | — | 0.074 | |
| CTC2024.02 | 0.086 | — | — | 0.1 | |
| ROUGE-22024.02 | 0.073 | — | — | 0.094 | |
| ROUGE-L2024.02 | 0.067 | — | — | 0.059 | |
| METEOR2026.05 | 0.051 | 0.059 | 0.065 | — | |
| BLEU2026.05 | 0.043 | 0.051 | 0.055 | — | |
| MoverScore2026.05 | 0.041 | 0.109 | 0.166 | — | |
| AlignScore2026.05 | 0.037 | 0.015 | 0.144 | — | |
| ROUGE-12026.05 | 0.029 | 0.109 | 0.129 | — | |
| QuestEval2026.05 | 0.02 | 0.077 | 0.17 | — | |
| ROUGE-22026.05 | 0.015 | 0.094 | 0.124 | — | |
| ROUGE-L2026.05 | 0.011 | 0.097 | 0.097 | — | |
| BARTScoreMetric Category=Trained, Training Dataset=CNNDM2023.07 | — | 0.289 | 0.238 | — | |
| BARTScoreMetric Category=Untrained2023.07 | — | 0.2 | 0.164 | — | |
| BERTScoreMetric Category=Untrained2023.07 | — | 0.219 | 0.156 | — | |
| CTRLEvalMetric Category=Untrained2023.07 | — | 0.195 | 0.177 | — | |
| DecompEvalMetric Category=Untrained2023.07 | — | 0.345 | 0.242 | — | |
| MoverScoreMetric Category=Untrained2023.07 | — | 0.19 | 0.153 | — | |
| ROUGE-1Metric Category=Untrained2023.07 | — | 0.17 | 0.115 | — | |
| ROUGE-LMetric Category=Untrained2023.07 | — | 0.169 | 0.103 | — | |
| UniEvalMetric Category=Trained, Training Dataset=Summ2023.07 | — | 0.333 | 0.225 | — | |
| UniEvalMetric Category=Trained, Training Dataset=Dial2023.07 | — | 0.291 | 0.194 | — |