# DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering Source: [DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering]() Collection index: [llms.txt]() Data updated: 2026-03-21T05:00:10.757Z Authors: Yilin Wang, Yuchun Fan, Jiaoyang Li, Ziming Zhu, Yongyu Mu, Qiaozhi He, Tong Xiao, Jingbo Zhu Published: 2026-03-19T16:23:04.000Z ## Abstract Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face the application scenario of retrieving across multilingual corpora and queries, leaving several open challenges. The first one involves the absence of benchmarks that assess RAG systems' capabilities under the multilingual multi-hop (MM-hop) QA setting. The second centers on the overreliance on LLMs' strong semantic understanding in English, which diminishes effectiveness in multilingual scenarios. To address these challenges, we first construct multilingual multi-hop QA benchmarks by translating English-only benchmarks into five languages, and then we propose DaPT, a novel multilingual RAG framework. DaPT generates sub-question graphs in parallel for both the source-language query and its English translation counterpart, then merges them before employing a bilingual retrieval-and-answer strategy to sequentially solve sub-questions. Our experimental results demonstrate that advanced RAG systems suffer from a significant performance imbalance in multilingual scenarios. Furthermore, our proposed method consistently yields more accurate and concise answers compared to the baselines, significantly enhancing RAG performance on this task. For instance, on the most challenging MuSiQue benchmark, DaPT achieves a relative improvement of 18.3\\% in average EM score over the strongest baseline. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multilingual Multi-hop Question Answering on HotpotQA sampled 1,000 questions (val)](): Multilingual Multi-hop Question Answering; HotpotQA sampled 1,000 questions (val); Swedish EM: 44.5. - [Multilingual Multi-hop Question Answering on MuSiQue sampled 1,000 questions (val)](): Multilingual Multi-hop Question Answering; MuSiQue sampled 1,000 questions (val); Swedish EM: 21.3. - [Multilingual Multi-hop Question Answering on 2WikiMultiHopQA (sampled 1k val)](): Multilingual Multi-hop Question Answering; 2WikiMultiHopQA sampled 1,000 questions (val); EM (Swedish): 46.5. ## Original sources and implementation [Original paper]() [PDF]()