List your company

Data-to-text evaluation on SFRES

0.389Spearman CorrelationHD-EVAL-NN
-0.004120.097940.20.30206Jun 22, 2021Apr 15, 2022Feb 7, 2023Dec 1, 2023Sep 24, 2024Jul 18, 2025May 12, 2026

Evaluation results

MethodLinks
HD-EVAL-NNIterative alignment training data percentage=50%, Aggregator type=NN2024.020.389——0.47
HD-EVAL-NNIterative alignment training data percentage=25%, Aggregator type=NN2024.020.363——0.453
UNIEVAL2024.020.354——0.381
GPT-4 EVAL2024.020.347——0.414
DecompEvalType=Instruction-tuned PLM (Zero-shot)2023.070.293———
UniEval (Summ)Training Dataset=SummEval2023.070.279———
DIFFSCORE-FT2026.050.2560.3220.354—
BARTSCORE2024.020.255——0.28
G-Eval2026.050.2470.2920.266—
UniEval (Dial)Training Dataset=Topical-Chat2023.070.243———
BARTSCORE-PROMPTFine-tuning=CNN/DM + Paraphrase, Prompt combination=true2021.060.238———
BARTScore2026.050.2030.270.201—
DIFFSCORE2026.050.1940.2240.303—
UniEval2026.050.1920.2160.246—
BARTSCORE-CNNFine-tuning=CNN/DM2021.060.191———
BARTSCORE-CNN-PARAFine-tuning=CNN/DM + Paraphrase2021.060.185———
GPTScore2026.050.1780.2130.237—
BARTSCOREFine-tuning=none2021.060.164———
BERTScore2021.060.156———
PRISM2021.060.155———
MoverScore2021.060.153———
BERTSCORE2024.020.145——0.164
BERTScore2026.050.1420.2050.154—
PRISM2024.020.126——0.146
ROUGE-22021.060.116———
ROUGE-12021.060.115———
ROUGE-L2021.060.103———
ROUGE-12024.020.092——0.074
CTC2024.020.086——0.1
ROUGE-22024.020.073——0.094
ROUGE-L2024.020.067——0.059
METEOR2026.050.0510.0590.065—
BLEU2026.050.0430.0510.055—
MoverScore2026.050.0410.1090.166—
AlignScore2026.050.0370.0150.144—
ROUGE-12026.050.0290.1090.129—
QuestEval2026.050.020.0770.17—
ROUGE-22026.050.0150.0940.124—
ROUGE-L2026.050.0110.0970.097—
BARTScoreMetric Category=Trained, Training Dataset=CNNDM2023.07—0.2890.238—
BARTScoreMetric Category=Untrained2023.07—0.20.164—
BERTScoreMetric Category=Untrained2023.07—0.2190.156—
CTRLEvalMetric Category=Untrained2023.07—0.1950.177—
DecompEvalMetric Category=Untrained2023.07—0.3450.242—
MoverScoreMetric Category=Untrained2023.07—0.190.153—
ROUGE-1Metric Category=Untrained2023.07—0.170.115—
ROUGE-LMetric Category=Untrained2023.07—0.1690.103—
UniEvalMetric Category=Trained, Training Dataset=Summ2023.07—0.3330.225—
UniEvalMetric Category=Trained, Training Dataset=Dial2023.07—0.2910.194—