# Generative Recommendation on ML OOD 10M Source: [Generative Recommendation on ML OOD 10M]() Collection index: [llms.txt]() Data updated: 2026-03-25T14:16:48.515Z Evaluation of generative recommendation models using the ML OOD 10M dataset, focusing on ranking metrics such as Hit Rate (H@K) and Novelty/Coverage (N@K) at K=10 and K=20. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Generative Recommendation | | Dataset (including any stated split) | ML OOD 10M | | Metric | Hit Rate @10 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Hit Rate @10](): Higher is better; unit: PERCENT. - [Novelty @10](): Higher is better; unit: PERCENT. - [Hit Rate @20](): Higher is better; unit: PERCENT. - [Novelty @20](): Higher is better; unit: PERCENT. ## Recorded results | Method | Hit Rate @10 | Result date | Report paper | | --- | --- | --- | --- | | CausalDPO | 61 | Not recorded | 69c36c1a0636e5bf4afc652a | | SDPO | 55 | Not recorded | 69c36c1a0636e5bf4afc652a | | SPRec | 55 | Not recorded | 69c36c1a0636e5bf4afc652a | | BIGRec | 53 | Not recorded | 69c36c1a0636e5bf4afc652a | | RosePO | 51 | Not recorded | 69c36c1a0636e5bf4afc652a | | SASRec | 50 | Not recorded | 69c36c1a0636e5bf4afc652a | | RW | 50 | Not recorded | 69c36c1a0636e5bf4afc652a | | D3 | 50 | Not recorded | 69c36c1a0636e5bf4afc652a | | DMPO | 44 | Not recorded | 69c36c1a0636e5bf4afc652a | | CausalDPO | 0.79 | Not recorded | 69c36c1a0636e5bf4afc652a | | RW | 0.77 | Not recorded | 69c36c1a0636e5bf4afc652a | | D3 | 0.72 | Not recorded | 69c36c1a0636e5bf4afc652a | | BIGRec | 0.66 | Not recorded | 69c36c1a0636e5bf4afc652a | | DMPO | 0.63 | Not recorded | 69c36c1a0636e5bf4afc652a | | SDPO | 0.6 | Not recorded | 69c36c1a0636e5bf4afc652a | | SPRec | 0.6 | Not recorded | 69c36c1a0636e5bf4afc652a | | RosePO | 0.58 | Not recorded | 69c36c1a0636e5bf4afc652a | | SASRec | 0.47 | Not recorded | 69c36c1a0636e5bf4afc652a | ### CausalDPO Hit Rate @10: 61. Result ID: 69c3edf347f34ce924adb464. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SDPO Hit Rate @10: 55. Result ID: 69c3edf347f34ce924adb461. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SPRec Hit Rate @10: 55. Result ID: 69c3edf347f34ce924adb463. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BIGRec Hit Rate @10: 53. Result ID: 69c3edf347f34ce924adb45d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RosePO Hit Rate @10: 51. Result ID: 69c3edf347f34ce924adb462. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SASRec Hit Rate @10: 50. Result ID: 69c3edf347f34ce924adb45c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RW Hit Rate @10: 50. Result ID: 69c3edf347f34ce924adb45e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### D3 Hit Rate @10: 50. Result ID: 69c3edf347f34ce924adb45f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DMPO Hit Rate @10: 44. Result ID: 69c3edf347f34ce924adb460. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CausalDPO Hit Rate @10: 0.79. Result ID: 69c3edf347f34ce924adb476. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base model":"Llama-3.1-8B","epochs":"3","negative sampling":"random sampling","distribution":"IID"}. This record does not assert independent reproduction. ### RW Hit Rate @10: 0.77. Result ID: 69c3edf347f34ce924adb470. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base model":"Llama-3.1-8B","epochs":"3","distribution":"IID"}. This record does not assert independent reproduction. ### D3 Hit Rate @10: 0.72. Result ID: 69c3edf347f34ce924adb471. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base model":"Llama-3.1-8B","epochs":"3","distribution":"IID"}. This record does not assert independent reproduction. ### BIGRec Hit Rate @10: 0.66. Result ID: 69c3edf347f34ce924adb46f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base model":"Llama-3.1-8B","epochs":"3","distribution":"IID"}. This record does not assert independent reproduction. ### DMPO Hit Rate @10: 0.63. Result ID: 69c3edf347f34ce924adb472. [Reporting paper]() Recorded evaluation configuration: {"base model":"Llama-3.1-8B","epochs":"3","negative samples":"single","distribution":"IID"}. This record does not assert independent reproduction. ### SDPO Hit Rate @10: 0.6. Result ID: 69c3edf347f34ce924adb473. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base model":"Llama-3.1-8B","epochs":"3","negative samples":"single","distribution":"IID"}. This record does not assert independent reproduction. ### SPRec Hit Rate @10: 0.6. Result ID: 69c3edf347f34ce924adb475. [Reporting paper]() Recorded evaluation configuration: {"base model":"Llama-3.1-8B","epochs":"3","negative samples":"single-iteration SFT output","distribution":"IID"}. This record does not assert independent reproduction. ### RosePO Hit Rate @10: 0.58. Result ID: 69c3edf347f34ce924adb474. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base model":"Llama-3.1-8B","epochs":"3","negative samples":"single","distribution":"IID"}. This record does not assert independent reproduction. ### SASRec Hit Rate @10: 0.47. Result ID: 69c3edf347f34ce924adb46e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"embedding dimension":"32","dropout rate":"0.1","distribution":"IID"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.