List your company

ResearchFormerly WizWand

ML1M

Benchmarks

TaskDatasetSOTA resultTrendResults

ML1M

45.23NDCG@20

81

Sequential Recommendation

ML1M

40.79HR@20

15

Positive Tag Controllable Recommendation

ML1M

0.575NDCG@10

14

Negative Suppression Recommendation

ML1M (test)

0.177NDCG@10

12

Positive Steering Recommendation

ML1M (test)

0.575NDCG@10

12

Generative Recommendation

ML1M

18.3Recall@10

7

Nuanced Semantic Request Fulfillment

ML1M

6.231Intent Fulfillment

4

Bias mitigation for recommendation

ML1M 1.0 (test)

3.5HR

4

ML1M Explicit Scenario

2.04HR@5

3

ML1M Implicit Scenario

0.023HR@5

3