paper-with-me

Papers

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation

2024-10-15 · Shuqiao Sun, Yutong Yao, Peiwen Wu, Feijun Jiang, Kaifu Zhang

Translation is important for cross-language communication, and many efforts have been made to improve its accuracy. However, less investment is conducted in aligning translations with human preferences, such as translation tones or styles. In this paper, a new method is proposed to effectively generate large-scale multilingual parallel corpora with specific translation preferences using Large Language Models (LLMs). Meanwhile, an automatic pipeline is designed to distill human preferences into smaller Machine Translation (MT) models for efficiently and economically supporting large-scale calls in online services. Experiments indicate that the proposed method takes the lead in translation tasks with aligned human preferences by a large margin. Meanwhile, on popular public benchmarks like WMT and Flores, on which our models were not trained, the proposed method also shows a competitive performance compared to SOTA works.

📄 PDF Abstract BibTeX arXiv:2410.11410

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization

2024-09-26 · Kaden Uhlig, Joern Wuebker, Raphael Reinauer, John DeNero

Reinforcement Learning from Human Feedback (RLHF) and derivative techniques like Direct Preference Optimization (DPO) are task-alignment algorithms used to repurpose general, foundational models for specific tasks. We sh…

Machine TranslationNMTTranslation

Code-Switched Text Synthesis in Unseen Language Pairs

2023-05-26 · I-Hung Hsu, Avik Ray, Shubham Garg, Nanyun Peng 외

Existing efforts on text synthesis for code-switching mostly require training on code-switched texts in the target language pairs, limiting the deployment of the models to cases lacking code-switched data. In this work, …

Machine Translation

PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features

2023-12-05 · Tianshun Han, Shengnan Gui, Yiqing Huang, Baihui Li 외

Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading to unsatisfactory results in terms of pr…

cross-modal alignmentDecoderspeech-recognitionSpeech Recognition+1

MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization

2024-01-12 · Shuaijie She, Wei Zou, ShuJian Huang, Wenhao Zhu 외

Though reasoning abilities are considered language-agnostic, existing LLMs exhibit inconsistent reasoning abilities across different languages, e.g., reasoning in the dominant language like English is superior to other l…

Mathematical Reasoning

Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization

2026-05-12 · Yilong Wang, Qianli Wang, Bohao Chu, Yihong Liu 외 arxiv

Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to …