Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding

• URL: http://arxiv.org/abs/2510.06866v1
• Date: Wed, 08 Oct 2025 10:37:17 GMT
• Title: Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
• Authors: Wafaa Mohammed, Vlad Niculae, Chrysoula Zerva,
• Abstract summary: Large language models (LLMs) have emerged as strong contenders in machine translation.<n>Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level.<n>We propose the use of quality-aware decoding (QAD) to effectively extract this knowledge.
• Score: 14.194775031266497
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective [53.594353527056775]
  We propose Chinese Commonsense Multi-hop Reasoning ( CCMOR) to evaluate Large Language Models (LLMs)<n> CCMOR is designed to evaluate LLMs' ability to integrate Chinese-specific factual knowledge with multi-step logical reasoning.<n>We implement a human-in-the-loop verification system, where domain experts systematically validate and refine the generated questions.
  arXiv  Detail & Related papers  (2025-10-09T20:29:00Z)
• How LLMs Learn: Tracing Internal Representations with Sparse Autoencoders [30.36521888592164]
  Large Language Models (LLMs) demonstrate remarkable multilingual capabilities and broad knowledge.<n>We analyze how the information encoded in LLMs' internal representations evolves during the training process.
  arXiv  Detail & Related papers  (2025-03-09T02:13:44Z)
• AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding [79.43306110124875]
  AlignVLM is a vision-text alignment method that maps visual features to a weighted average of text embeddings.<n>Our experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods.
  arXiv  Detail & Related papers  (2025-02-03T13:34:51Z)
• Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage [50.84150600032693]
  Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations.<n>We propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions.<n>Our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V.
  arXiv  Detail & Related papers  (2024-12-20T01:37:22Z)
• Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach [7.5069214839655345]
  Large language models (LLMs) have demonstrated remarkable proficiency in machine translation (MT) We propose a multi-step prompt chain that enhances translation faithfulness by prioritizing key terms crucial for semantic accuracy. Experiments using Llama and Qwen as base models on the FLORES-200 and WMT datasets demonstrate significant improvements over baselines.
  arXiv  Detail & Related papers  (2024-11-13T05:40:24Z)
• Context-Aware or Context-Insensitive? Assessing LLMs' Performance in Document-Level Translation [10.174848090916669]
  Large language models (LLMs) are increasingly strong contenders in machine translation.<n>We focus on document-level translation, where some words cannot be translated without context from outside the sentence.
  arXiv  Detail & Related papers  (2024-10-18T11:52:10Z)
• Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning [38.89119606657543]
  In contrast to sentence-level translation, document-level translation (DOCMT) by large language models (LLMs) based on in-context learning faces two major challenges. We propose a Context-Aware Prompting method (CAP) to generate more accurate, cohesive, and coherent translations via in-context learning. We conduct extensive experiments across various DOCMT tasks, and the results demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-06-11T09:11:17Z)
• Teaching Machines to Code: Smart Contract Translation with LLMs [4.780973517287942]
  We present a pioneering approach, which harnesses the synergy of two distinct large language models (LLMs) within a unified framework. This framework is designed to grasp coding principles and apply this understanding to the translation of code into an unfamiliar language. Our study delves into the capacity of LLMs to mimic human learning processes, offering an in-depth evaluation of our methodology for converting smart contracts written in Solidity to Move.
  arXiv  Detail & Related papers  (2024-03-13T18:55:20Z)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation [64.5862977630713]
  This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task. We find that reference information significantly enhances the evaluation accuracy, while surprisingly, source information sometimes is counterproductive.
  arXiv  Detail & Related papers  (2024-01-12T13:23:21Z)
• Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks [68.79880423713597]
  We introduce a method that utilizes the ASR system's lattice output instead of relying solely on the top hypothesis. Our in-context learning experiments, covering spoken question answering and intent classification, underline the LLM's resilience to noisy speech transcripts.
  arXiv  Detail & Related papers  (2024-01-05T17:58:10Z)
• IERL: Interpretable Ensemble Representation Learning -- Combining CrowdSourced Knowledge and Distributed Semantic Representations [11.008412414253662]
  Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Recent studies have shown that LLMs tend to generate unintended, inconsistent, or wrong texts as outputs. We propose a novel ensemble learning method, Interpretable Ensemble Representation Learning (IERL), that systematically combines LLM and crowdsourced knowledge representations.
  arXiv  Detail & Related papers  (2023-06-24T05:02:34Z)
• Exploring Human-Like Translation Strategy with Large Language Models [93.49333173279508]
  Large language models (LLMs) have demonstrated impressive capabilities in general scenarios. This work proposes the MAPS framework, which stands for Multi-Aspect Prompting and Selection. We employ a selection mechanism based on quality estimation to filter out noisy and unhelpful knowledge.
  arXiv  Detail & Related papers  (2023-05-06T19:03:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.