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

Books

Benchmarks

Task NameDataset NameSOTA ResultTrend
FluencyBOOKS
Fluency Score4.46
28
Next-item predictionBooks Industrial dataset (test)
Hits@1081.62
22
Node classificationBooks
Accuracy92.44
21
Sequential RecommendationBooks Amazon (test)
HR@2000.2173
20
Node ClassificationBooks History
Accuracy56
17
LLM UnlearningBOOKS
VerMem0
16
RecommendationBooks
Recall@1017.86
16
Trustworthiness evaluationBooks
Avg F196.7
16
OOD detectionBooks-History
FPR@9536.03
13
Sequential RecommendationBooks (test)
HR@107.74
12
Graph Anomaly DetectionBooks
AUC65.6
10
Hierarchical Text ClassificationBooks
Macro F161.2
10
RecommendationBooks InstructRec retrospective (test)
HR@149.9
9
RecommendationBooks N=20 (test)
Hit Rate @ 142.36
9
Speculative DecodingBooks BookCorpusOpen
Speedup3.32
8
RecommendationBooks
HR@112.51
8
Continual RecommendationBooks
Average Metric4.22
8
RecommendationBooks (test)
NDCG@205.93
8
Attribute estimationBooks
Hits@1090.77
8
Personalized review generationBooks
ROUGE-133.18
7
Speculative DecodingBooks
Speedup3.32
6
Collaborative RankingBooks
H@1026.73
6
Personalized RecommendationBooks (Light User)
H@162
5
Personalized RecommendationBooks Active User
Hit Rate @ 151
5
RecommendationBooks
Speedup Ratio (k=10)35.5
4
Showing 25 of 29 rows