arXiv Computation and Language

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

The paper introduces Cross-Preference Learning (CPL), a training framework that explicitly models the complementary strengths of sentence-level and context-aware machine translation. By incorporating intra- and cross-condition preferences into the optimization objective, CPL provides targeted supervision to leverage useful contextual signals while remaining robust to uninformative context. Experiments on multiple public context-aware MT tasks with models such as Qwen3-4B, Qwen3-8B, and Llama-3-8B-Instruct show consistent improvements in translation quality and robustness without altering the model architecture.

arXiv Computation and Language
Sep 1

Beyond "To whom it may concern": Tailoring Machine Translation to Audience and Intent

The paper investigates how machine translation can be tailored to specific audiences and intents, a capability enabled by large language models (LLMs). By systematically evaluating purpose-driven MT across 50 languages, 5 model sizes, and 8 text domains, the authors find that explicit instructions significantly improve translation adaptiveness, especially for informal domains, larger models, and higher-resource languages. They also show that traditional MT metrics often penalize adapted translations and that models can self-generate useful instructions from context, closing a large portion of the adaptiveness gap.

By Raphael Merx, Ekaterina Vylomova, Trevor Cohn
Hugging Face Trending Papers
Jul 20

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training the model to distinguish good and bad tokens in a response, we naturally guide the model towards generating good tokens, while avoiding the pitfalls that come with directly training the model to generate off-policy tokens.

arXiv AI
Jun 4

SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization

arXiv:2505. 11166v3 Announce Type: replace-cross Abstract: Despite advances in pretraining with extended context sizes, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primarily due to insufficient long-context alignment caused by data quality issues, training inefficiencies, and the lack of well-designed optimization objectives.

By Huashan Sun, Shengyi Liao, Yansen Han, Yu Bai, Yang Gao, Cheng Fu, Weizhou Shen, Fanqi Wan, Ming Yan, Ji Zhang, Fei Huang
arXiv Computation and Language
Aug 25

Syntax-Guided Diffusion Language Models with User-Integrated Personalization

The paper introduces a syntax-guided diffusion language model that incorporates structural supervision and personalized conditioning to improve text quality, diversity, and controllability. It presents a cascaded framework generating syntactic guidance before text generation, and a novel noncascaded architecture for better structure-content alignment. A shared representation mechanism enables fine‑grained personalization across users, achieving faithful stylistic generation and zero‑shot inference, with experiments showing superior fluency, diversity, and stylistic fidelity.

By Ruqian Zhang, Yijiao Zhang, Juan Shen, Zhongyi Zhu, Annie Qu
arXiv Machine Learning
3d ago

Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation

The paper introduces Retrieval-Augmented Decoding (RAD), a decoding-time method that improves the truthfulness of large language models without retraining. RAD uses a small reference set of up to ten annotated examples to build a grounding space of context embeddings and next-token logits, which it retrieves and aggregates during inference to shape the model’s output. Experiments on four open-ended generation benchmarks and four different LLMs show that RAD consistently outperforms strong baselines and generalizes well across tasks.

By Manh Nguyen, Sunil Gupta, Hung Le
arXiv AI
Sep 2

Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation

The paper introduces Iterative MBR Distillation for Error Span Detection (ESD) in machine translation, a self‑evolution framework that replaces human annotations with pseudo‑labels generated by a large language model. By iteratively applying Minimum Bayes Risk decoding, the method produces high‑quality error spans without costly human effort. Experiments on WMT Metrics Shared Task datasets show that models trained solely on these pseudo‑labels outperform both unadapted baselines and supervised models trained on human data at system and span levels, while keeping sentence‑level performance competitive.

By Boxuan Lyu, Haiyue Song, Zhi Qu
arXiv AI
Jun 9

Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation

arXiv:2606. 08011v1 Announce Type: cross Abstract: Although directly prompting off-the-shelf Large Language Models (LLMs) to generate meaning-preserving source rewrites can effectively enhance Machine Translation (MT) quality, doing so requires manually tuning prompts for different MT models.

By Boxuan Lyu, Haiyue Song, Zhi Qu, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura