# UML Relationship Generation on English specifications dataset Full (test) Source: [UML Relationship Generation on English specifications dataset Full (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:39:46.149Z Evaluation of model performance on generating UML relationships using the full test split of the English specifications dataset, measured by connectivity similarity and size difference. 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 | UML Relationship Generation | | Dataset (including any stated split) | English specifications dataset Full (test) | | Metric | Connectivity Similarity | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 1 of 1 | | 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 - [Connectivity Similarity](): Higher is better; unit: PERCENT. - [Size Difference](): Lower is better; unit: PERCENT. ## Recorded results | Method | Connectivity Similarity | Result date | Report paper | | --- | --- | --- | --- | | Proposed Approach | 63.9 | Not recorded | 68fa6dc51e209131cea3c07f | ### Proposed Approach Connectivity Similarity: 63.9. Result ID: 698fe77f3a6c314849fcb007. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Matching protocol":"General matching"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.