# Question Answering on NQ poison @ Position 10, k=10 (test) Source: [Question Answering on NQ poison @ Position 10, k=10 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:02:23.812Z Evaluation of model performance on the Natural Questions (NQ) dataset under a specific poisoning attack configuration (Position 10, k=10), measured by Robustness Accuracy. 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 | Question Answering | | Dataset (including any stated split) | NQ poison @ Position 10, k=10 (test) | | Metric | Robustness Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Robustness Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Robustness Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MIS | 65.8 | Not recorded | 68fa7bb31e209131cea89fbe | | Vanilla RAG | 63.6 | Not recorded | 68fa7bb31e209131cea89fbe | | MIS | 60.4 | Not recorded | 68fa7bb31e209131cea89fbe | | RobustRAG | 58.8 | Not recorded | 68fa7bb31e209131cea89fbe | | MIS | 58 | Not recorded | 68fa7bb31e209131cea89fbe | | AstuteRAG | 56.8 | Not recorded | 68fa7bb31e209131cea89fbe | | InstructRAG | 54.8 | Not recorded | 68fa7bb31e209131cea89fbe | | RobustRAG | 52.8 | Not recorded | 68fa7bb31e209131cea89fbe | | InstructRAG | 52 | Not recorded | 68fa7bb31e209131cea89fbe | | AstuteRAG | 51 | Not recorded | 68fa7bb31e209131cea89fbe | | AstuteRAG | 50.6 | Not recorded | 68fa7bb31e209131cea89fbe | | InstructRAG | 47 | Not recorded | 68fa7bb31e209131cea89fbe | | RobustRAG | 44.4 | Not recorded | 68fa7bb31e209131cea89fbe | | Vanilla RAG | 42.8 | Not recorded | 68fa7bb31e209131cea89fbe | | Vanilla RAG | 41.6 | Not recorded | 68fa7bb31e209131cea89fbe | ### MIS Robustness Accuracy: 65.8. Result ID: 699a88f55698665ec4131789. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini","k":10}. This record does not assert independent reproduction. ### Vanilla RAG Robustness Accuracy: 63.6. Result ID: 699a88f55698665ec4131785. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini","k":10}. This record does not assert independent reproduction. ### MIS Robustness Accuracy: 60.4. Result ID: 699a88f55698665ec4131784. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3.2-3B","k":10}. This record does not assert independent reproduction. ### RobustRAG Robustness Accuracy: 58.8. Result ID: 699a88f55698665ec4131788. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini","k":10}. This record does not assert independent reproduction. ### MIS Robustness Accuracy: 58. Result ID: 699a88f55698665ec413177f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Mistral-7B","k":10}. This record does not assert independent reproduction. ### AstuteRAG Robustness Accuracy: 56.8. Result ID: 699a88f55698665ec4131786. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini","k":10}. This record does not assert independent reproduction. ### InstructRAG Robustness Accuracy: 54.8. Result ID: 699a88f55698665ec4131787. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini","k":10}. This record does not assert independent reproduction. ### RobustRAG Robustness Accuracy: 52.8. Result ID: 699a88f55698665ec4131783. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama3.2-3B","k":10}. This record does not assert independent reproduction. ### InstructRAG Robustness Accuracy: 52. Result ID: 699a88f55698665ec413177d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Mistral-7B","k":10}. This record does not assert independent reproduction. ### AstuteRAG Robustness Accuracy: 51. Result ID: 699a88f55698665ec4131781. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3.2-3B","k":10}. This record does not assert independent reproduction. ### AstuteRAG Robustness Accuracy: 50.6. Result ID: 699a88f55698665ec413177c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Mistral-7B","k":10}. This record does not assert independent reproduction. ### InstructRAG Robustness Accuracy: 47. Result ID: 699a88f55698665ec4131782. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3.2-3B","k":10}. This record does not assert independent reproduction. ### RobustRAG Robustness Accuracy: 44.4. Result ID: 699a88f55698665ec413177e. [Reporting paper]() Recorded evaluation configuration: {"Model":"Mistral-7B","k":10}. This record does not assert independent reproduction. ### Vanilla RAG Robustness Accuracy: 42.8. Result ID: 699a88f55698665ec4131780. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama3.2-3B","k":10}. This record does not assert independent reproduction. ### Vanilla RAG Robustness Accuracy: 41.6. Result ID: 699a88f55698665ec413177b. [Reporting paper]() Recorded evaluation configuration: {"Model":"Mistral-7B","k":10}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.