PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationTranslationSimilar Papers 제목 키워드 기반
Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization
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 TranslationNMTTranslationCode-Switched Text Synthesis in Unseen Language Pairs
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 TranslationPMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features
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+1MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
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 ReasoningMacro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization
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 …