# Continual Generative Information Retrieval on Natural Questions Source: [Continual Generative Information Retrieval on Natural Questions]() Collection index: [llms.txt]() Data updated: 2026-04-28T08:00:32.123Z Evaluation of model performance on the Natural Questions dataset specifically focusing on Continual Generative Information Retrieval tasks, measured using metrics like D0-D5, AP, FWT, and BWT. 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 | Continual Generative Information Retrieval | | Dataset (including any stated split) | Natural Questions | | Metric | D0 Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [D0 Score](): Higher is better; unit: SCALAR. - [D1 Score](): Higher is better; unit: SCALAR. - [D2 Score](): Higher is better; unit: SCALAR. - [D3 Score](): Higher is better; unit: SCALAR. - [D4 Score](): Higher is better; unit: SCALAR. - [D5 Score](): Higher is better; unit: SCALAR. - [AP](): Higher is better; unit: PERCENT. - [Forward Transfer (FWT)](): Higher is better; unit: SCALAR. - [Backward Transfer (BWT)](): Higher is better; unit: SCALAR. ## Recorded results | Method | D0 Score | Result date | Report paper | | --- | --- | --- | --- | | LoRA-SPQ | 80.34 | Not recorded | 69f03ef155a3c32af89f9f4a | | Full FT-SPQ | 80.34 | Not recorded | 69f03ef155a3c32af89f9f4a | | PAMT-LoRA-SPQ | 80.34 | Not recorded | 69f03ef155a3c32af89f9f4a | | PAMT-Full FT-SPQ | 80.34 | Not recorded | 69f03ef155a3c32af89f9f4a | | DPR-HN | 78.41 | Not recorded | 69f03ef155a3c32af89f9f4a | | MixLoRA-DSI | 77.89 | Not recorded | 69f03ef155a3c32af89f9f4a | | DPR | 77.21 | Not recorded | 69f03ef155a3c32af89f9f4a | | CLEVER | 75.42 | Not recorded | 69f03ef155a3c32af89f9f4a | | LoRA-TU | 74.28 | Not recorded | 69f03ef155a3c32af89f9f4a | | Full FT-TU | 74.28 | Not recorded | 69f03ef155a3c32af89f9f4a | | PAMT-LoRA-TU | 74.28 | Not recorded | 69f03ef155a3c32af89f9f4a | | PAMT-Full FT-TU | 74.28 | Not recorded | 69f03ef155a3c32af89f9f4a | | BM25 | 73.78 | Not recorded | 69f03ef155a3c32af89f9f4a | | DSI++ | 72.15 | Not recorded | 69f03ef155a3c32af89f9f4a | | CorpusBrain++ | 70.58 | Not recorded | 69f03ef155a3c32af89f9f4a | | PromptDSI | 68.92 | Not recorded | 69f03ef155a3c32af89f9f4a | ### LoRA-SPQ D0 Score: 80.34. Result ID: 69f0684f47f34ce924d6183a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Adaptation Stage":"Stage 1: Base adaptation","Tuning Strategy":"LoRA","DocID Design":"SPQ"}. This record does not assert independent reproduction. ### Full FT-SPQ D0 Score: 80.34. Result ID: 69f0684f47f34ce924d6183c. [Reporting paper]() Recorded evaluation configuration: {"Adaptation Stage":"Stage 1: Base adaptation","Tuning Strategy":"Full FT","DocID Design":"SPQ"}. This record does not assert independent reproduction. ### PAMT-LoRA-SPQ D0 Score: 80.34. Result ID: 69f0684f47f34ce924d6183e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adaptation Stage":"Stage 2: Post-Adaptation Memory Tuning","Tuning Strategy":"LoRA","DocID Design":"SPQ"}. This record does not assert independent reproduction. ### PAMT-Full FT-SPQ D0 Score: 80.34. Result ID: 69f0684f47f34ce924d61840. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adaptation Stage":"Stage 2: Post-Adaptation Memory Tuning","Tuning Strategy":"Full FT","DocID Design":"SPQ"}. This record does not assert independent reproduction. ### DPR-HN D0 Score: 78.41. Result ID: 69f0684f47f34ce924d61834. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Expanded protocol","Decoding Strategy":"constrained decoding"}. This record does not assert independent reproduction. ### MixLoRA-DSI D0 Score: 77.89. Result ID: 69f0684f47f34ce924d61839. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"PEFT-based continual GenIR baselines","Evaluation Protocol":"Expanded protocol"}. This record does not assert independent reproduction. ### DPR D0 Score: 77.21. Result ID: 69f0684f47f34ce924d61833. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Expanded protocol","Decoding Strategy":"constrained decoding"}. This record does not assert independent reproduction. ### CLEVER D0 Score: 75.42. Result ID: 69f0684f47f34ce924d61836. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Non-PEFT continual GenIR baselines","Evaluation Protocol":"Expanded protocol"}. This record does not assert independent reproduction. ### LoRA-TU D0 Score: 74.28. Result ID: 69f0684f47f34ce924d6183b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Adaptation Stage":"Stage 1: Base adaptation","Tuning Strategy":"LoRA","DocID Design":"TU"}. This record does not assert independent reproduction. ### Full FT-TU D0 Score: 74.28. Result ID: 69f0684f47f34ce924d6183d. [Reporting paper]() Recorded evaluation configuration: {"Adaptation Stage":"Stage 1: Base adaptation","Tuning Strategy":"Full FT","DocID Design":"TU"}. This record does not assert independent reproduction. ### PAMT-LoRA-TU D0 Score: 74.28. Result ID: 69f0684f47f34ce924d6183f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adaptation Stage":"Stage 2: Post-Adaptation Memory Tuning","Tuning Strategy":"LoRA","DocID Design":"TU"}. This record does not assert independent reproduction. ### PAMT-Full FT-TU D0 Score: 74.28. Result ID: 69f0684f47f34ce924d61841. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adaptation Stage":"Stage 2: Post-Adaptation Memory Tuning","Tuning Strategy":"Full FT","DocID Design":"TU"}. This record does not assert independent reproduction. ### BM25 D0 Score: 73.78. Result ID: 69f0684f47f34ce924d61832. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Expanded protocol","Decoding Strategy":"constrained decoding"}. This record does not assert independent reproduction. ### DSI++ D0 Score: 72.15. Result ID: 69f0684f47f34ce924d61835. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Non-PEFT continual GenIR baselines","Evaluation Protocol":"Expanded protocol"}. This record does not assert independent reproduction. ### CorpusBrain++ D0 Score: 70.58. Result ID: 69f0684f47f34ce924d61837. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"PEFT-based continual GenIR baselines","Evaluation Protocol":"Expanded protocol"}. This record does not assert independent reproduction. ### PromptDSI D0 Score: 68.92. Result ID: 69f0684f47f34ce924d61838. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"PEFT-based continual GenIR baselines","Evaluation Protocol":"Expanded protocol"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.