# Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translation

arXiv: https://arxiv.org/abs/2603.25183 · HTML: https://mlsanity.com/paper/2603.25183/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 30 of 33)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://mlsanity.com/paper/1805.10163/) (2018)
- [Neural Machine Translation with Extended Context](https://mlsanity.com/paper/1708.05943/) (2017)
- [Large language models effectively leverage document-level context for literary translation, but critical errors persist](https://mlsanity.com/paper/2304.03245/) (2023)
- [Adapting Large Language Models for Document-Level Machine Translation](https://mlsanity.com/paper/2401.06468/) (2024)
- [BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation](https://mlsanity.com/paper/2103.11878/) (2021)
- [Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metric](https://mlsanity.com/paper/2209.13654/) (2022)
- [Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer](https://mlsanity.com/paper/2205.11631/) (2022)
- [Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2311.08380/) (2023)
- [DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory](https://mlsanity.com/paper/2410.08143/) (2024)
- [Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning](https://mlsanity.com/paper/2406.07081/) (2024)
- [The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities](https://mlsanity.com/paper/2405.20089/) (2024)
- [Word Alignment as Preference for Machine Translation](https://mlsanity.com/paper/2405.09223/) (2024)
- [Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions](https://mlsanity.com/paper/2401.08088/) (2024)
- [Multilingual Contextualization of Large Language Models for Document-Level Machine Translation](https://mlsanity.com/paper/2504.12140/) (2025)
- [Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation](https://mlsanity.com/paper/2410.20941/) (2024)
- [Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation](https://mlsanity.com/paper/2410.07779/) (2024)
- [Source-primed Multi-turn Conversation Helps Large Language Models Translate Documents](https://mlsanity.com/paper/2503.10494/) (2025)
- [DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators](https://mlsanity.com/paper/2402.15200/) (2024)
- [Context-Aware or Context-Insensitive? Assessing LLMs' Performance in Document-Level Translation](https://mlsanity.com/paper/2410.14391/) (2024)
- [Doc-Guided Sent2Sent++: A Sent2Sent++ Agent with Doc-Guided memory for Document-level Machine Translation](https://mlsanity.com/paper/2501.08523/) (2025)
- [Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization](https://mlsanity.com/paper/2409.17673/) (2024)

## Built on by (most cited first, 2 of 2)

- [STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation](https://mlsanity.com/paper/2608.27161/) (2026)
- [Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking](https://mlsanity.com/paper/2609.12674/) (2026)

## Abstract (arXiv)

Context-aware machine translation (MT) leverages document-level information, yet it does not consistently outperform sentence-level MT, as contextual signals are unevenly beneficial across sentences. Existing training objectives do not explicitly model this variability, limiting a model's ability to adaptively exploit context. In this paper, we propose Cross-Preference Learning (CPL), a preference-based training framework that explicitly captures the complementary benefits of sentence-level and context-aware MT. CPL achieves this by integrating both intra- and cross-condition preferences into the preference optimization objective, providing explicit supervision to exploit informative context while remaining robust to uninformative context. We validate the proposed approach on several public context-aware MT tasks using multiple models, including Qwen3-4B, Qwen3-8B, and Llama-3-8B-Instruct. Experimental results demonstrate consistent improvements in translation quality and robustness across both input conditions, achieved without any architectural modifications.