paper-with-me

홈 › Papers

EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation

2025-09-24 · Sen Yang, Yu Bao, Yu Lu, Jiajun Chen, Shujian Huang, Shanbo Cheng arxiv

Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation. This work addresses this limitation through a synthetic data generation framework that leverages models' established English-to-x (en2x) capabilities. By extending English parallel corpora into omnidirectional datasets and developing an English-referenced quality evaluation proxy, we enable effective collection of high-quality x2x training data. Combined with preference-based optimization, our method achieves significant improvement across 72 x2x directions for widely used LLMs, while generalizing to enhance en2x performance. The results demonstrate that strategic exploitation of English-centric strengths can bootstrap comprehensive multilingual translation capabilities in LLMs. We release codes, datasets, and model checkpoints at https://github.com/NJUNLP/EAX

📄 PDF Abstract BibTeX arXiv:2509.19770

Code (0)

등록된 구현이 없습니다.

Tasks

Synthetic Data GenerationMachine Translation

Similar Papers 제목 키워드 기반

Predicting Anchored Text from Translation Memories for Machine Translation Using Deep Learning Methods

2024-09-26 · Richard Yue, John E. Ortega

Translation memories (TMs) are the backbone for professional translation tools called computer-aided translation (CAT) tools. In order to perform a translation using a CAT tool, a translator uses the TM to gather transla…

Machine TranslationTranslation

APO: Alpha-Divergence Preference Optimization

2025-12-28 · Wang Zixian arxiv

Two divergence regimes dominate modern alignment practice. Supervised fine-tuning and many distillation-style objectives implicitly minimize the forward KL divergence KL(q || pi_theta), yielding stable mode-covering upda…

Reinforcement Learning

Landmark-based consonant voicing detection on multilingual corpora

2016-11-10 · Xiang Kong, Xuesong Yang, Mark Hasegawa-Johnson, Jeung-Yoon Choi 외

This paper tests the hypothesis that distinctive feature classifiers anchored at phonetic landmarks can be transferred cross-lingually without loss of accuracy. Three consonant voicing classifiers were developed: (1) man…

Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation

2025-11-24 · Ruiying Liu, Yuanzhi Liang, Haibin Huang, Tianshu Yu 외 arxiv

Group Relative Policy Optimization (GRPO) has emerged as an effective and lightweight framework for post-training visual generative models. However, its performance is fundamentally limited by the ambiguity of textual vi…

Video Generation

Semi-Anchored Detector for One-Stage Object Detection

2020-09-10 · Lei Chen, Qi Qian, Hao Li

A standard one-stage detector is comprised of two tasks: classification and regression. Anchors of different shapes are introduced for each location in the feature map to mitigate the challenge of regression for multi-sc…

ClassificationGeneral ClassificationObjectobject-detection+2