# Generative Retrieval on NQ new documents Source: [Generative Retrieval on NQ new documents]() Collection index: [llms.txt]() Data updated: 2026-03-04T20:10:05.111Z Evaluation of Generative Retrieval performance on the Natural Questions (NQ) dataset using the 'new documents' configuration, measured by ranking metrics such as Recall at K (R@K) and Mean Reciprocal Rank (MRR). 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 Retrieval | | Dataset (including any stated split) | NQ new documents | | Metric | R@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [R@1](): Higher is better; unit: PERCENT. - [R@10](): Higher is better; unit: PERCENT. - [R@100](): Higher is better; unit: PERCENT. - [MRR@100](): Higher is better; unit: PERCENT. ## Recorded results | Method | R@1 | Result date | Report paper | | --- | --- | --- | --- | | From Scratch | 69.3 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | DOME | 68.6 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | DSI++ | 67.4 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | New-Doc FT | 66 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | DPR | 64.7 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | AlphaEdit | 61.6 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | MEMIT | 60.9 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | BM25 | 36.5 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | ROME | 20.1 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | DSI | 7.1 | Not recorded | 69a7bc7b2d603e6de3e3d416 | | Ultron | 6.4 | Not recorded | 69a7bc7b2d603e6de3e3d416 | ### From Scratch R@1: 69.3. Result ID: 69a891996dbb7075b9513871. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DOME R@1: 68.6. Result ID: 69a891996dbb7075b9513877. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"TPD (s)":"2.14\*"}. This record does not assert independent reproduction. ### DSI++ R@1: 67.4. Result ID: 69a891996dbb7075b9513873. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"TPD (s)":"3.54"}. This record does not assert independent reproduction. ### New-Doc FT R@1: 66. Result ID: 69a891996dbb7075b9513872. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"TPD (s)":"3.42"}. This record does not assert independent reproduction. ### DPR R@1: 64.7. Result ID: 69a891996dbb7075b951386e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AlphaEdit R@1: 61.6. Result ID: 69a891996dbb7075b9513876. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"TPD (s)":"12.12"}. This record does not assert independent reproduction. ### MEMIT R@1: 60.9. Result ID: 69a891996dbb7075b9513875. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"TPD (s)":"12.62"}. This record does not assert independent reproduction. ### BM25 R@1: 36.5. Result ID: 69a891996dbb7075b951386d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ROME R@1: 20.1. Result ID: 69a891996dbb7075b9513874. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"TPD (s)":"20.23"}. This record does not assert independent reproduction. ### DSI R@1: 7.1. Result ID: 69a891996dbb7075b951386f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ultron R@1: 6.4. Result ID: 69a891996dbb7075b9513870. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.