# Attribute-controlled Machine Translation on MT-GENEVAL (aggregated) Source: [Attribute-controlled Machine Translation on MT-GENEVAL (aggregated)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:36:55.647Z Evaluation of Machine Translation performance where the output must adhere to specific controlled attributes, using the aggregated MT-GENEVAL dataset. 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 | Attribute-controlled Machine Translation | | Dataset (including any stated split) | MT-GENEVAL (aggregated) | | Metric | BLEU | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [BLEU](): Higher is better; unit: SCALAR. - [COMET](): Higher is better; unit: SCALAR. - [L-Acc](): Higher is better; unit: SCALAR. - [S-Acc](): Higher is better; unit: SCALAR. ## Recorded results | Method | BLEU | Result date | Report paper | | --- | --- | --- | --- | | Adapted MT | 0.396 | Not recorded | 68fa707c1e209131cea4b65a | | BLOOM 175B RAMP | 0.343 | Not recorded | 68fa707c1e209131cea4b65a | | BLOOM 175B base | 0.333 | Not recorded | 68fa707c1e209131cea4b65a | | BLOOM 175B +mark | 0.331 | Not recorded | 68fa707c1e209131cea4b65a | | BLOOM 175B RAMP (Cross-Lingual) | 0.294 | Not recorded | 68fa707c1e209131cea4b65a | | BLOOM 175B base (Cross-Lingual) | 0.285 | Not recorded | 68fa707c1e209131cea4b65a | | XGLM 7.5B RAMP | 0.248 | Not recorded | 68fa707c1e209131cea4b65a | | XGLM 7.5B base | 0.237 | Not recorded | 68fa707c1e209131cea4b65a | | XGLM 7.5B +mark | 0.237 | Not recorded | 68fa707c1e209131cea4b65a | ### Adapted MT BLEU: 0.396. Result ID: 6991443c3a6c31484906e7f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Setting":"Same-Language"}. This record does not assert independent reproduction. ### BLOOM 175B RAMP BLEU: 0.343. Result ID: 6991443c3a6c31484906e7ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BLOOM 175B","Prompting Setting":"Same-Language","Variant":"RAMP","In-context Examples":"16"}. This record does not assert independent reproduction. ### BLOOM 175B base BLEU: 0.333. Result ID: 6991443c3a6c31484906e7ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BLOOM 175B","Prompting Setting":"Same-Language","Variant":"base","In-context Examples":"16"}. This record does not assert independent reproduction. ### BLOOM 175B +mark BLEU: 0.331. Result ID: 6991443c3a6c31484906e7ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BLOOM 175B","Prompting Setting":"Same-Language","Variant":"attribute marking (+mark)","In-context Examples":"16"}. This record does not assert independent reproduction. ### BLOOM 175B RAMP (Cross-Lingual) BLEU: 0.294. Result ID: 6991443c3a6c31484906e7f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BLOOM 175B","Prompting Setting":"Cross-Lingual","Variant":"RAMP","In-context Examples":"16"}. This record does not assert independent reproduction. ### BLOOM 175B base (Cross-Lingual) BLEU: 0.285. Result ID: 6991443c3a6c31484906e7f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BLOOM 175B","Prompting Setting":"Cross-Lingual","Variant":"base","In-context Examples":"16"}. This record does not assert independent reproduction. ### XGLM 7.5B RAMP BLEU: 0.248. Result ID: 6991443c3a6c31484906e7ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XGLM 7.5B","Prompting Setting":"Same-Language","Variant":"RAMP","In-context Examples":"16"}. This record does not assert independent reproduction. ### XGLM 7.5B base BLEU: 0.237. Result ID: 6991443c3a6c31484906e7ea. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"XGLM 7.5B","Prompting Setting":"Same-Language","Variant":"base","In-context Examples":"16"}. This record does not assert independent reproduction. ### XGLM 7.5B +mark BLEU: 0.237. Result ID: 6991443c3a6c31484906e7eb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"XGLM 7.5B","Prompting Setting":"Same-Language","Variant":"attribute marking (+mark)","In-context Examples":"16"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.