Publications Preprint · 2025

MTRACE: Multilingual Retrieval-Augmented Generation for Temporally Diverse Text Corpora

S. Bakkali, A. Mudet

arXiv preprint

In one paragraph

A modular multilingual RAG pipeline evaluated on the French and English subsets of MIRACL: semantic query expansion with reciprocal rank fusion, a generation prompt that enforces strict grounding and explicit abstention, and ablations on entity extraction and retriever choice. It gives faithful answers for well-supported queries and abstains correctly on unanswerable ones.

Version 1 (December 2025) was titled “Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question Answering”.

Cite

@misc{bakkali2025mtrace,
  title         = {{MTRACE: Multilingual Retrieval-Augmented Generation for Temporally Diverse Text Corpora}},
  author        = {Bakkali, Souhail and Mudet, Anthony},
  eprint        = {2512.12694},
  archivePrefix = {arXiv},
  year          = {2025},
  url           = {https://arxiv.org/abs/2512.12694}
}