{"id":43779,"date":"2026-11-13T10:59:21","date_gmt":"2026-11-13T10:59:21","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/farabi-at-wmt-2026-post-hoc-channel-controllers-for-low-resource-arabic-asian-machine-translation\/"},"modified":"2026-11-13T10:59:21","modified_gmt":"2026-11-13T10:59:21","slug":"farabi-at-wmt-2026-post-hoc-channel-controllers-for-low-resource-arabic-asian-machine-translation","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/farabi-at-wmt-2026-post-hoc-channel-controllers-for-low-resource-arabic-asian-machine-translation\/","title":{"rendered":"FARABI at WMT 2026: Post-Hoc Channel Controllers for Low-Resource Arabic\u2013Asian Machine Translation"},"content":{"rendered":"<p>We describe our submission to the WMT26 Low-Resource Arabic-Asian Language Translation shared task covering ten translation directions between Arabic and five Asian languages. Our central question is whether a post-hoc controller can improve translation quality beyond a fine-tuned backbone without modifying any model weight. For the five into-Arabic directions, our primary system jointly fine-tunes facebook\/nllb-200-3.3B on all source languages and augments it at inference time with per-direction NTK-Mirror controllers (fewer than 6K parameters per direction) that rescale frozen transformer output channels. For the five from-Arabic directions, the backbone is QWEN2.5-7B-INSTRUCT adapted via QLoRA, likewise augmented with NTK-Mirror. In the official evaluation, our system ranked first on Bengali- and Indonesian-to-Arabic, second on Hindi- and Urdu-to-Arabic, and third on English-to-Arabic, placing in the top three on all five into-Arabic directions. Post-submission analysis indicates that the weaker from-Arabic results stem primarily from a model-selection decision at submission time.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We describe our submission to the WMT26 Low-Resource Arabic-Asian Language Translation shared task covering ten translation directions between Arabic and five Asian languages. Our central question is whether a post-hoc controller can improve translation quality beyond a fine-tuned backbone without modifying any model weight. For the five into-Arabic directions, our primary system jointly fine-tunes facebook\/nllb-200-3.3B on all source languages and augments it at inference time with per-direction NTK-Mirror controllers (fewer [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"publication-year":[1680],"class_list":["post-43779","publication","type-publication","status-publish","hentry","publication-type-inproceedings","publication-year-1680"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/43779","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/43779\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=43779"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=43779"},{"taxonomy":"publication-year","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-year?post=43779"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}