Personalized Text Generation
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
0.401ROUGE-L
64
Feb 26, 2026
51.6R-1 Score
14
Jun 2, 2026
19.3ROUGE-1 Recall
14
Jun 2, 2026
0.273R-1
14
May 27, 2026
53.5ROUGE-1 Score
13
Jun 2, 2026
54.2ROUGE-1
8
Jun 5, 2026
49.8ROUGE-1
8
Jun 5, 2026
21ROUGE-1
8
Jun 5, 2026
74Alignment Score
7
Feb 26, 2026
21.02ROUGE-L
6
Mar 10, 2026
26.68ROUGE-L
6
Mar 10, 2026
37.27ROUGE-L
6
Mar 10, 2026
99.8User-level Accuracy (GT)
5
Jun 1, 2026
95.4Accuracy (User-level, GT)
5
Jun 1, 2026
100User-level Accuracy (GT)
5
Jun 1, 2026
20.3ROUGE
5
May 13, 2026
22.6ROUGE
5
May 13, 2026
27.1ROUGE
5
May 13, 2026
47.7ROUGE
5
May 13, 2026
21.8ROUGE
5
May 13, 2026
15.662Personalization ROUGE-1
5
Apr 23, 2026
16.1ROUGE-1 (Personalization)
5
Apr 23, 2026
1.65LLM-as-a-Judge Score
4
Jun 4, 2026
2.03LLM-as-a-Judge Score
4
Jun 4, 2026
2.15LLM-as-a-Judge Score
4
Jun 4, 2026