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

ML1M

Benchmarks

Task NameDataset NameSOTA ResultTrend
RecommendationML1M
NDCG@2045.23
81
Sequential RecommendationML1M
HR@2040.79
15
Positive Tag Controllable RecommendationML1M
NDCG@100.5748
14
Negative Suppression RecommendationML1M (test)
NDCG@100.1772
12
Positive Steering RecommendationML1M (test)
NDCG@100.5748
12
Generative RecommendationML1M
Recall@1018.3
7
Nuanced Semantic Request FulfillmentML1M
Intent Fulfillment6.231
4
Bias mitigation for recommendationML1M 1.0 (test)
HR3.5
4
RecommendationML1M Explicit Scenario
HR@52.04
3
RecommendationML1M Implicit Scenario
HR@50.0226
3
Showing 10 of 10 rows