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 show that applying task-alignment to neural machine translation (NMT) addresses an existing task--data mismatch in NMT, leading to improvements across all languages of a multilingual model, even when task-alignment is only applied to a subset of those languages. We do so by introducing Direct Quality Optimization (DQO), a variant of DPO leveraging a pre-trained translation quality estimation model as a proxy for human preferences, and verify the improvements with both automatic metrics and human evaluation.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Language Model Alignment in Multilingual Trolley Problems
We evaluate the moral alignment of large language models (LLMs) with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200…
Decision MakingEthicsFairnessLanguage Modeling+2PMMT: 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 translati…
Machine TranslationTranslationImplicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual prefe…
Instruction FollowingTransfer LearningReuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at sca…
PolyAlign: Conditional Human-Distribution Alignment
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective for improving average helpfulness, this ca…