多语言RAG系统中的质量感知翻译标注
Quality-Aware Translation Tagging in Multilingual RAG system
AI总结：
提出QTT-RAG，通过评估翻译质量并附加分数元数据，提升多语言RAG在低资源场景下的响应生成性能，优于现有基线。
摘要：
多语言检索增强生成（mRAG）在低资源场景下通常检索英文文档并将其翻译成查询语言。然而，较差的翻译质量会降低响应生成性能。现有方法要么假设翻译质量足够，要么利用重写方法，这会导致事实扭曲和幻觉。为缓解这些问题，我们提出了mRAG中的质量感知翻译标注（QTT-RAG），该方法沿三个维度显式评估翻译质量——语义等价性、语法准确性和自然度与流畅性——并将这些分数作为元数据附加，而不改变原始内容。我们在两个开放域问答基准（XORQA、MKQA）上，使用六种指令微调的大语言模型（参数规模从2.4B到14B），涵盖两种低资源语言（韩语和芬兰语）和一种高资源语言（中文），将QTT-RAG与基线CrossRAG和DKM-RAG进行了评估。QTT-RAG通过保持事实完整性，同时使生成模型能够基于翻译可靠性做出明智决策，从而优于基线方法。该方法允许在原生语言文档有限的低资源环境中有效利用跨语言文档，为多语言领域提供了一种实用且稳健的解决方案。
英文摘要：
Multilingual Retrieval-Augmented Generation (mRAG) often retrieves English documents and translates them into the query language for low-resource settings. However, poor translation quality degrades response generation performance. Existing approaches either assume sufficient translation quality or utilize the rewriting method, which introduces factual distortion and hallucinations. To mitigate these problems, we propose Quality-Aware Translation Tagging in mRAG (QTT-RAG), which explicitly evaluates translation quality along three dimensions-semantic equivalence, grammatical accuracy, and naturalness&fluency-and attach these scores as metadata without altering the original content. We evaluate QTT-RAG against CrossRAG and DKM-RAG as baselines in two open-domain QA benchmarks (XORQA, MKQA) using six instruction-tuned LLMs ranging from 2.4B to 14B parameters, covering two low-resource languages (Korean and Finnish) and one high-resource language (Chinese). QTT-RAG outperforms the baselines by preserving factual integrity while enabling generator models to make informed decisions based on translation reliability. This approach allows for effective usage of cross-lingual documents in low-resource settings with limited native language documents, offering a practical and robust solution across multilingual domains.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
