{"paper":{"title":"Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carlos Escolano, Ernesto Garcia-Estrada, Jos\\'e A. R. Fonallosa","submitted_at":"2026-05-15T14:11:23Z","abstract_excerpt":"Production machine translation relies overwhelmingly on encoder-decoder Seq2Seq models, yet reinforcement learning approaches to MT fine-tuning have largely targeted decoder-only LLMs at $\\geq$7B parameters, with limited systematic study of encoder-decoder architectures. We apply Group Relative Policy Optimization to NLLB-200 (600M and 1.3B) using a hybrid reference-free reward (LaBSE and COMET-Kiwi) that requires no parallel data at fine-tuning time, evaluating across 13 typologically diverse languages. GRPO yields consistent improvements on all 13 languages, up to $+$5.03 chrF++ for Traditio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15976","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15976/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:44.864180Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.683966Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b7ba2e7b7a19dbeacc06af55080bfb9d356b99332f1a04a1ca8137255a560695"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}