更好的分解，自由聚合：面向多语言多跳问答的合成器折叠框架
Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
浏览论文内容
中文总结 AI 辅助
针对多语言多跳问答中现有方法的翻译噪声与错误放大问题，提出Syfer框架，通过推迟翻译、格式受限分解与质量检查实现性能与成本的良好平衡。
中文摘要 AI 辅助
多语言检索增强生成（mRAG）使大型语言模型能够获取全球分布的外部知识，用于复杂的多语言问答任务。近期的方法要么将检索到的文档翻译成英语或查询语言以弥合跨语言语义差距，要么将复杂查询分解为子问题并聚合中间推理过程。然而，这两类工作都存在两个局限：其一，一刀切的翻译对齐方式会丢弃目标语言特有的文化和语言原生信息，引入翻译噪声并增加系统成本；其二，贪心式分解与聚合会产生冗余子问题，在逐步推理中放大错误，最终的推理路径聚合会进一步加剧这些错误。我们提出了Syfer（一种面向多语言多跳问答的合成器折叠框架）来解决这两个问题，该框架默认推迟翻译而非直接应用翻译。Syfer首先调用格式受限的分解器以生成原语言中的子问题图，随后进行分解质量检查；当检查通过时，在目标语言中采用“先检索后回答”策略依次回答子问题，仅当检查不通过时才激活带有双语子问题图对齐的英语翻译路径。在多种语言上的实验表明，Syfer在达到有竞争力的准确率的同时，在性能与计算成本之间取得了良好的平衡。
英文摘要
Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex multilingual question answering. Recent approaches either translate retrieved documents into English or the query language to bridge the cross-lingual semantic gap, or decompose a complex query into sub-questions and aggregate the intermediate reasoning process. However, both lines of work suffer from two limitations. First, one-size-fits-all translation alignment, blanket translation discards culturally and linguistically native information unique to the target language, introduces translation noise, and inflates system cost. Second, greedy decomposition and aggregation, uncontrolled decomposition produces redundant sub-questions that compound errors during step-wise reasoning, and the final aggregation over reasoning paths further amplifies these errors. We address both with our method Syfer, a synthesizer-folding framework for multilingual multi-hop question answering that defers translation rather than applying it by default. Syfer first invokes a format-constrained decomposer to produce a sub-question graph in the original language, followed by a decomposition-quality check; when the check passes, sub-questions are answered sequentially under a retrieve-then-answer policy in the target language, and the English translation pathway with bilingual sub-question graph alignment is activated only when the check fails. Experiments across multiple languages show that Syfer attains competitive accuracy while striking a favourable balance between performance and computational cost.
发表机构
- School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）
- Kunming University of Science and Technology（昆明理工大学）
机构由 AI 辅助整理，请以论文原文为准。
