Image de couverture de livre

Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zou, Wei, Yang, Sen, Bao, Yu, Huang, Shujian, Chen, Jiajun, Cheng, Shanbo
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions
par: Li, Jiahuan, et autres
Publié: (2023)

MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation
par: Li, Jiahuan, et autres
Publié: (2024)

EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation
par: Yang, Sen, et autres
Publié: (2025)

GRRM: Group Relative Reward Modeling for Machine Translation
par: Yang, Sen, et autres
Publié: (2026)

Extend Adversarial Policy Against Neural Machine Translation via Unknown Token
par: Zou, Wei, et autres
Publié: (2025)

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
par: Zhu, Wenhao, et autres
Publié: (2023)

TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning
par: Huang, Xu, et autres
Publié: (2026)

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
par: Ding, Peng, et autres
Publié: (2025)

The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights
par: Zhu, Wenhao, et autres
Publié: (2024)

Question Translation Training for Better Multilingual Reasoning
par: Zhu, Wenhao, et autres
Publié: (2024)

Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation
par: Huang, Xu, et autres
Publié: (2024)

Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge
par: Li, Jiahuan, et autres
Publié: (2024)

EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling
par: Zhang, Shimao, et autres
Publié: (2024)

MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
par: She, Shuaijie, et autres
Publié: (2024)

Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation
par: Geng, Xiang, et autres
Publié: (2025)

Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners
par: Zhang, Shimao, et autres
Publié: (2024)

MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing
par: Zhou, Hao, et autres
Publié: (2024)

Multi-Candidate Speculative Decoding
par: Yang, Sen, et autres
Publié: (2024)

Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation
par: Ranathungaa, Surangika, et autres
Publié: (2024)

Multilingual Contrastive Decoding via Language-Agnostic Layers Skipping
par: Zhu, Wenhao, et autres
Publié: (2024)

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
par: She, Shuaijie, et autres
Publié: (2025)

Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models
par: Gao, Changjiang, et autres
Publié: (2024)

G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation
par: Pan, Xingyuan, et autres
Publié: (2024)

Large Language Models are Limited in Out-of-Context Knowledge Reasoning
par: Hu, Peng, et autres
Publié: (2024)

Exploring the Factual Consistency in Dialogue Comprehension of Large Language Models
par: She, Shuaijie, et autres
Publié: (2023)

Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models
par: Shang, Yuzhe, et autres
Publié: (2026)

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
par: Huang, Xu, et autres
Publié: (2025)

Self-Improving Multilingual Long Reasoning via Translation-Reasoning Integrated Training
par: Liu, Junxiao, et autres
Publié: (2026)

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$Δ$ Integration into Upcycled MoE
par: Zhou, Hao, et autres
Publié: (2026)

Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters
par: Cheng, Shanbo, et autres
Publié: (2025)

PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment
par: Li, Jiahuan, et autres
Publié: (2024)

From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition
par: Wang, Tianduo, et autres
Publié: (2025)

G-Zero: Self-Play for Open-Ended Generation from Zero Data
par: Huang, Chengsong, et autres
Publié: (2026)

Self-Evolution Knowledge Distillation for LLM-based Machine Translation
par: Song, Yuncheng, et autres
Publié: (2024)

Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data
par: Ji, Shaoxiong, et autres
Publié: (2025)

Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly
par: Gao, Changjiang, et autres
Publié: (2024)

Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning
par: Zhao, Chunxu, et autres
Publié: (2026)

Revealing the Parallel Multilingual Learning within Large Language Models
par: Mu, Yongyu, et autres
Publié: (2024)

SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation
par: Xu, Ting, et autres
Publié: (2025)

How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective
par: Zhang, Shimao, et autres
Publié: (2025)