Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering

• URL: http://arxiv.org/abs/2608.13160v1
• Date: Thu, 13 Aug 2026 12:25:59 GMT
• Title: Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
• Abstract summary: We introduce Syfer, a framework for multilingual multi-hop question answering.<n>Syfer defers translation rather than applying it by default.<n> Experiments across multiple languages show that Syfer attains competitive accuracy.
• Score: 48.94279718429342
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Multilingual Reasoning Cascades Need More Context [36.84122814591169]
  We show that a context-aware translation cascade provides the original question, the English translated question, and the reasoning trace to the context of the final translation module.<n>Our study emphasizes the need to better design information flow in machine translation cascades for mitigating error propagation.
  arXiv  Detail & Related papers  (2026-06-25T17:26:46Z)
• Disentangling Language Roles in Multilingual LLM Task Execution [17.182371695349385]
  MTM-Bench is a benchmark for language-conditioned task execution.<n>It enumerates all 27 triplets and contains 2,430 instances per model across semantic reversal, final-state extraction, and language purity.<n>We evaluate 20 frontier and open-weight LLMs using metrics for semantic correctness, target-language adherence, constraint satisfaction, contamination ratio, and joint success.
  arXiv  Detail & Related papers  (2026-05-26T20:09:34Z)
• DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering [41.923993964253405]
  We propose a novel framework for retrieving across multilingual corpora and queries.<n>DaPT generates sub-question graphs in parallel for both the source-language query and its English translation counterpart.<n>DaPT consistently yields more accurate and concise answers compared to the baselines.
  arXiv  Detail & Related papers  (2026-03-19T16:23:04Z)
• Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches [8.127643463046516]
  We examine strategies to improve the multilingual and crosslingual performance.<n>We evaluate approaches on a dataset containing posts and claims in 47 languages.<n>Most importantly, we show that crosslinguality is a setup with its own unique characteristics compared to the multilingual setup.
  arXiv  Detail & Related papers  (2025-05-28T08:47:10Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.<n>We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.<n>We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision [44.04243892727856]
  Cross-lingual open domain question answering is a complex problem. We show that CLQA can be addressed using a single encoder-decoder model. We propose a self-supervised method based on exploiting the cross-lingual link structure within Wikipedia.
  arXiv  Detail & Related papers  (2024-02-26T11:42:29Z)
• Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval [80.43859162884353]
  We propose a multilingual multilingual language model called masked sentence model (MSM)<n>MSM consists of a sentence encoder to generate the sentence representations, and a document encoder applied to a sequence of sentence vectors from a document.<n>To train the model, we propose a masked sentence prediction task, which masks and predicts the sentence vector via a hierarchical contrastive loss with sampled negatives.
  arXiv  Detail & Related papers  (2023-02-03T09:54:27Z)
• Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation [80.16548523140025]
  We extend the vanilla pretrain-finetune pipeline with extra code-switching restore task to bridge the gap between the pretrain and finetune stages. Our approach could narrow the cross-lingual sentence representation distance and improve low-frequency word translation with trivial computational cost.
  arXiv  Detail & Related papers  (2022-04-16T16:08:38Z)
• Zero-Shot Cross-lingual Semantic Parsing [56.95036511882921]
  We study cross-lingual semantic parsing as a zero-shot problem without parallel data for 7 test languages. We propose a multi-task encoder-decoder model to transfer parsing knowledge to additional languages using only English-Logical form paired data. Our system frames zero-shot parsing as a latent-space alignment problem and finds that pre-trained models can be improved to generate logical forms with minimal cross-lingual transfer penalty.
  arXiv  Detail & Related papers  (2021-04-15T16:08:43Z)
• Multilingual Answer Sentence Reranking via Automatically Translated Data [97.98885151955467]
  We present a study on the design of multilingual Answer Sentence Selection (AS2) models, which are a core component of modern Question Answering (QA) systems. The main idea is to transfer data, created from one resource rich language, e.g., English, to other languages, less rich in terms of resources.
  arXiv  Detail & Related papers  (2021-02-20T03:52:08Z)

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.