Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation

• URL: http://arxiv.org/abs/2604.16881v1
• Date: Sat, 18 Apr 2026 07:15:43 GMT
• Title: Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation
• Abstract summary: We propose EA-RLVR (Entity-Anchored Reinforcement Learning with Verifiable Rewards) to incentivize the effective use of parametric knowledge.<n>EA-RLVR anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization.<n>We evaluate EA-RLVR on XC-Translate and observe consistent improvements in both entity translation accuracy and out-of-domain generalization.
• Score: 68.85147984815778
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-cultural entity translation remains challenging for large language models (LLMs) as literal or phonetic renderings are usually yielded instead of culturally appropriate translations in context. However, relevant knowledge may already be encoded in model parameters during large-scale pre-training. To incentivize the effective use of parametric knowledge, we propose EA-RLVR (Entity-Anchored Reinforcement Learning with Verifiable Rewards), a training framework that optimizes cross-cultural entity translation without relying on external knowledge bases. EA-RLVR anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization. This design steers the model toward learning a robust reasoning process rather than merely imitating reference translations. We evaluate EA-RLVR on XC-Translate and observe consistent improvements in both entity translation accuracy and out-of-domain generalization. Specifically, training on merely 7k samples boosts Qwen3-14B's entity translation accuracy from 23.66\% to 31.87\% on a 50k test set comprising entirely unseen entities. The learned entity translation ability also transfers to general translation, yielding +1.35 XCOMET on WMT24++, which scales to +1.59 with extended optimization. Extensive analyses of $pass@k$ dynamics and reward formulations attribute these gains to superior sampling efficiency and a stable optimization landscape.

Related papers

• Backtranslation Augmented Direct Preference Optimization for Neural Machine Translation [39.28410239503065]
  We introduce a novel framework that requires only a general text corpus and an expert translator which can be either human or an AI system to provide iterative feedback.<n>Applying our DPO-driven framework to the gemma3-1b model yields a significant improvement in translation quality.
  arXiv  Detail & Related papers  (2026-04-28T14:29:06Z)
• ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation [63.89730738735446]
  We propose ReflectMT, a two-stage reflection internalization algorithm for machine translation.<n>Our approach develops the model's "translate-reflect-refine" capability through reinforcement learning.<n> Experimental results on datasets such as WMT24 demonstrate that our model's first-pass translations during inference outperform multi-step reasoning LRMs.
  arXiv  Detail & Related papers  (2026-04-21T06:48:41Z)
• PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning [54.19784655270799]
  We introduce textbfPEGRL, a textittwo-stage RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization.<n>Experiments on English$to$Finnish, English$to$Turkish, and English$leftrightarrow$Chinese show consistent gains over RL baselines.
  arXiv  Detail & Related papers  (2026-02-03T10:22:55Z)
• Reflective Translation: Improving Low-Resource Machine Translation via Structured Self-Reflection [0.15229257192293197]
  Low-resource languages such as isiZulu and isiXhosa face persistent challenges in machine translation due to limited parallel data and linguistic resources.<n>Recent advances in large language models suggest that self-reflection, prompting a model to critique and revise its own outputs, can improve reasoning quality and factual consistency.<n>This paper introduces Reflective Translation, a prompt-based framework in which a model generates an initial translation, produces a structured self-critique, and then uses this reflection to generate a refined translation.
  arXiv  Detail & Related papers  (2026-01-27T18:37:09Z)
• EffiReasonTrans: RL-Optimized Reasoning for Code Translation [48.862761776440635]
  EffiReasonTrans is a training framework designed to improve translation accuracy while balancing inference latency.<n>EffiReasonTrans consistently improves translation accuracy (up to +49.2% CA and +27.8% CodeBLEU compared to the base model) while reducing the number of generated tokens.
  arXiv  Detail & Related papers  (2025-10-21T17:55:39Z)
• How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizes [2.0109318570325847]
  We investigate the impact of fine-tuning the Llama 3 model using TMs from a specific organisation in the software sector. We fine-tune separate models for each training set and evaluate their performance based on automatic metrics, BLEU, chrF++, TER, and COMET. Our findings reveal improvement in translation performance with larger datasets across all metrics.
  arXiv  Detail & Related papers  (2024-09-05T12:06:38Z)
• Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution [57.42593422091653]
  We explore leveraging reinforcement learning with human feedback to improve translation quality. A reward model with strong language capabilities can more sensitively learn the subtle differences in translation quality.
  arXiv  Detail & Related papers  (2024-02-18T09:51:49Z)
• Improving Neural Machine Translation by Bidirectional Training [85.64797317290349]
  We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. Experimental results show that BiT pushes the SOTA neural machine translation performance across 15 translation tasks on 8 language pairs significantly higher.
  arXiv  Detail & Related papers  (2021-09-16T07:58:33Z)

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.