# Interactive Query Answering on FB15k237 manually curated preference sets Source: [Interactive Query Answering on FB15k237 manually curated preference sets]() Collection index: [llms.txt]() Data updated: 2026-03-27T14:28:56.944Z Evaluation of interactive query answering performance on the manually curated preference sets derived from the FB15k-237 knowledge graph, reporting metrics such as Average MRR, Pairwise Accuracy, and NDCG@10. 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 | Interactive Query Answering (Average MRR) | | Dataset (including any stated split) | FB15k237 manually curated preference sets | | Metric | Metric 1p | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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 - [Metric 1p](): Higher is better; unit: PERCENT. - [Average Pairwise Accuracy](): Higher is better; unit: PERCENT. - [Average MRR](): Higher is better; unit: PERCENT. - [Average NDCG@10](): Higher is better; unit: PERCENT. - [Metric 2p](): Higher is better; unit: PERCENT. - [Metric 3p](): Higher is better; unit: PERCENT. - [Metric 2i](): Higher is better; unit: PERCENT. - [Metric 3i](): Higher is better; unit: PERCENT. - [Metric ip](): Higher is better; unit: PERCENT. - [Metric pi](): Higher is better; unit: PERCENT. - [Metric 2in](): Higher is better; unit: PERCENT. - [Metric 3in](): Higher is better; unit: PERCENT. - [Metric inp](): Higher is better; unit: PERCENT. - [Metric pin](): Higher is better; unit: PERCENT. - [Metric pni](): Higher is better; unit: PERCENT. - [Metric 2u](): Higher is better; unit: PERCENT. - [Metric up](): Higher is better; unit: PERCENT. - [Average Metric (avg)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Metric 1p | Result date | Report paper | | --- | --- | --- | --- | | NQR | 27.54 | Not recorded | 68fa7abf1e209131cea84f6e | | Cosine | 22.9 | Not recorded | 68fa7abf1e209131cea84f6e | | Unconstrained | 19.22 | Not recorded | 68fa7abf1e209131cea84f6e | | LightGBM | 16.6 | Not recorded | 68fa7abf1e209131cea84f6e | ### NQR Metric 1p: 27.54. Result ID: 69c6933647f34ce924b0efda. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Cosine Metric 1p: 22.9. Result ID: 69c6933647f34ce924b0efd9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Unconstrained Metric 1p: 19.22. Result ID: 69c6933647f34ce924b0efd7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LightGBM Metric 1p: 16.6. Result ID: 69c6933647f34ce924b0efd8. [Reporting 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.