# Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question Answering

arXiv: https://arxiv.org/abs/2512.12694 · HTML: https://mlsanity.com/paper/2512.12694/

## Key facts

- Cited by 2 papers in the map (data through 14 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.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 15 of 15)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection](https://mlsanity.com/paper/2007.11464/) (2020)
- [Survey of Computational Approaches to Lexical Semantic Change](https://mlsanity.com/paper/1811.06278/) (2018)
- [Challenges for Computational Lexical Semantic Change](https://mlsanity.com/paper/2101.07668/) (2021)
- [The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America](https://mlsanity.com/paper/2005.01583/) (2020)
- [Using Word Embeddings for Automatic Query Expansion](https://mlsanity.com/paper/1606.07608/) (2016)

## Built on by (most cited first, 2 of 2)

- [ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.17012/) (2026)
- [TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives](https://mlsanity.com/paper/2609.19897/) (2026)

## 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/