用质量感知解码让大模型更好理解长文语篇
Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
- 提出质量感知解码，从大模型中挖掘语篇知识
- 提升译文语义丰富度，更贴近人类偏好
- 适合关注长文档翻译与语篇连贯性的研究者
大语言模型在机器翻译中表现强劲，但在处理语篇现象（如代词消解、词汇衔接）方面仍存在不足。本研究深入探讨了大模型在上下文感知翻译中的语篇表现，证明其内部编码了语篇知识，并提出质量感知解码（QAD）方法以有效提取该知识。通过全面分析，QAD在多项指标上优于其他解码策略，显著提升了译文的语义丰富性，并使其更符合人类偏好。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。