Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective

• URL: http://arxiv.org/abs/2605.15976v1
• Date: Fri, 15 May 2026 14:11:23 GMT
• Title: Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective
• Abstract summary: GRPO yields consistent improvements on all 13 languages, up to $+$5.03 chrF++ for Traditional Chinese, and, without any target-language data, competes with 3-epoch supervised fine-tuning on morphologically complex languages.<n>We identify a consistent empirical pattern in which gains are largest where baseline performance is weakest and reward discriminability is highest.
• Score: 1.786053901581251
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 Traditional Chinese, and, without any target-language data, competes with 3-epoch supervised fine-tuning on morphologically complex languages . We identify a consistent empirical pattern in which gains are largest where baseline performance is weakest and reward discriminability is highest, making this approach most effective precisely where parallel data is scarcest, and replicate this pattern across English and Spanish source languages.

Related papers

• Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models [102.20309135516186]
  Cross-entropy (CE) training provides dense and scalable supervision for language models.<n>We introduce a feature-matching objective for language-model fine-tuning.<n>To optimize this objective efficiently, we propose energy-based fine-tuning.
  arXiv  Detail & Related papers  (2026-03-12T17:57:50Z)
• Cost-Aware Model Selection for Text Classification: Multi-Objective Trade-offs Between Fine-Tuned Encoders and LLM Prompting in Production [0.0]
  Large language models (LLMs) have demonstrated strong capabilities in open-ended reasoning and generative language tasks.<n>For structured text classification problems with fixed label spaces, model selection is often driven by predictive performance alone.<n>We show that fine-tuned encoder-based models from the BERT family achieve competitive, and often superior, classification performance.
  arXiv  Detail & Related papers  (2026-02-06T03:54:28Z)
• Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation [8.896718697354187]
  XL-CoGen produces high-quality code across multiple programming languages.<n>It integrates intermediate representation, code generation, translation, and automated repair.
  arXiv  Detail & Related papers  (2025-09-24T09:18:08Z)
• NL in the Middle: Code Translation with LLMs and Intermediate Representations [56.77064674776534]
  Large language models (LLMs) produce buggy code translations.<n>One promising avenue to improve translation accuracy is through intermediate representations.<n>We investigate whether LLM-based code translation can benefit from intermediate representations.
  arXiv  Detail & Related papers  (2025-07-11T14:29:21Z)
• Improving Language and Modality Transfer in Translation by Character-level Modeling [14.145120349133007]
  Current translation systems, despite being highly multilingual, cover only 5% of the world's languages.<n>We propose a character-based approach to improve adaptability to new languages and modalities.
  arXiv  Detail & Related papers  (2025-05-30T13:16:08Z)
• Bielik v3 Small: Technical Report [0.0]
  We introduce Bielik v3, a series of parameter-efficient generative text models (1.5B and 4.5B) optimized for Polish language processing.<n>These models demonstrate that smaller, well-optimized architectures can achieve performance comparable to much larger counterparts.
  arXiv  Detail & Related papers  (2025-05-05T10:39:51Z)
• Pushing the boundary on Natural Language Inference [49.15148871877941]
  Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering and information retrieval.<n>Despite its importance, current NLI systems heavily rely on learning with limiting artifacts and biases, inference and real-world applicability.<n>This work provides a framework for building robust NLI systems without sacrificing quality or real-world applicability.
  arXiv  Detail & Related papers  (2025-04-25T14:20:57Z)
• Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data [64.4458540273004]
  We propose a self-play framework that leverages only monolingual data and the intrinsic multilingual knowledge of Large Language Models (LLMs)<n>Experiments demonstrate that this approach not only matches the performance of models trained on large-scale parallel data but also excels in non-English translation directions.
  arXiv  Detail & Related papers  (2025-04-20T16:20:30Z)
• Distributionally Robust Multilingual Machine Translation [94.51866646879337]
  We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
  arXiv  Detail & Related papers  (2021-09-09T03:48:35Z)
• Exploring Unsupervised Pretraining Objectives for Machine Translation [99.5441395624651]
  Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT) Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence architectures, by masking parts of the input and reconstructing them in the decoder. We compare masking with alternative objectives that produce inputs resembling real (full) sentences, by reordering and replacing words based on their context.
  arXiv  Detail & Related papers  (2021-06-10T10:18:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.