mlsanityData to 7 Oct 2026

Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question Answering

arXiv 2512.12694 ↗First posted 14 Dec 2025cs.DL cs.CVcited by 2

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Large multilingual knowledge bases expose temporally diverse information, yet retrieval quality remains sensitive to lexical variation and cross-lingual terminology shifts. We develop and evaluate MTRACE (Multilingual Temporal Retrieval-Augmented Generation with evidence grounding), a pipeline designed to test whether query expansion and multi-query fusion mitigate vocabulary mismatch in temporally layered text corpora, on the French and English subsets of MIRACL. Our approach integrates: (i) semantic query expansion (SQE) and multi-query fusion via Reciprocal Rank Fusion (RRF), targeting retrieval stability under query variation; (ii) a generation prompt enforcing strict grounding in retrieved evidence and explicit abstention when evidence is insufficient; and (iii) a modular architecture enabling systematic component evaluation. Ablation studies on Named Entity Recognition (NER) and embedding model selection demonstrate the importance of syntactic coherence in entity extraction and of self-retrieval and efficiency measurements for retriever selection. Our end-to-end evaluation over 50 constructed queries shows faithful answers for well-supported queries, correct abstention on unanswerable questions, and no re-scored similarity gains from multi-query fusion over single-query dense retrieval. By scoping our claims to a clean, text-only baseline, we separate these effects from OCR-noise confounds; direct measurement of diachronic lexical drift is left to future work. Code and configurations are available at urlhttps://anonymous.4open.science/r/MIRAGE-8EAA/

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 15 of its 31 references that are in the map. First posted on arXiv 14 Dec 2025.

Builds on

15 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 13

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  2. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  3. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  5. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  6. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  7. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 283
  8. 2020Directions in Abusive Language Training Data: Garbage In, Garbage Outcited by 139
  9. 2020SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detectioncited by 105
  10. 2018Survey of Computational Approaches to Lexical Semantic Changecited by 60
  11. 2021Challenges for Computational Lexical Semantic Changecited by 15
  12. 2016Using Word Embeddings for Automatic Query Expansioncited by 14
1 more
  1. 2020The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling Americacited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ORDER: Task-Conditioned Routing for Retrieval-Augmented Generationcited by 0
  2. 2026TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archivescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Retrieval to Generation: Comparing Different Approaches
  2. 2026All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
  3. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  4. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  5. 2026EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
  6. 2026XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation
  7. 2020Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval
  8. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation