# Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding

arXiv: https://arxiv.org/abs/2510.06866 · HTML: https://mlsanity.com/paper/2510.06866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 50 of its 82 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 30 of 50)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation](https://mlsanity.com/paper/2005.10283/) (2020)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [Neural Machine Translation with Extended Context](https://mlsanity.com/paper/1708.05943/) (2017)
- [Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation](https://mlsanity.com/paper/1808.07048/) (2018)
- [Evaluating Discourse Phenomena in Neural Machine Translation](https://mlsanity.com/paper/1711.00513/) (2017)
- [Document-Level Neural Machine Translation with Hierarchical Attention Networks](https://mlsanity.com/paper/1809.01576/) (2018)
- [WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects](https://mlsanity.com/paper/2502.12404/) (2025)
- [Improving the Transformer Translation Model with Document-Level Context](https://mlsanity.com/paper/1810.03581/) (2018)
- [Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation](https://mlsanity.com/paper/2108.04718/) (2021)
- [Selective Attention for Context-aware Neural Machine Translation](https://mlsanity.com/paper/1903.08788/) (2019)
- [Adapting Large Language Models for Document-Level Machine Translation](https://mlsanity.com/paper/2401.06468/) (2024)
- [Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation](https://mlsanity.com/paper/2105.08504/) (2021)
- [Exploiting Cross-Sentence Context for Neural Machine Translation](https://mlsanity.com/paper/1704.04347/) (2017)
- [Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models](https://mlsanity.com/paper/2009.13267/) (2020)
- [M-Prometheus: A Suite of Open Multilingual LLM Judges](https://mlsanity.com/paper/2504.04953/) (2025)
- [When Does Translation Require Context? A Data-driven, Multilingual Exploration](https://mlsanity.com/paper/2109.07446/) (2021)
- [DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence](https://mlsanity.com/paper/2201.11176/) (2022)
- [Gender Bias in Large Language Models across Multiple Languages](https://mlsanity.com/paper/2403.00277/) (2024)
- [Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation](https://mlsanity.com/paper/2005.03393/) (2020)

## Abstract (arXiv)

Large language models (LLMs) have emerged as strong contenders in machine translation.Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In this study, we thoroughly investigate the discourse phenomena performance of LLMs in context-aware translation. We demonstrate that discourse knowledge is encoded within LLMs and propose the use of quality-aware decoding (QAD) to effectively extract this knowledge, showcasing its superiority over other decoding approaches through comprehensive analysis. Furthermore, we illustrate that QAD enhances the semantic richness of translations and aligns them more closely with human preferences.