When a Reranking Bonus Becomes a Language Filter: Score-Scale Mismatch in Reciprocal Rank Fusion for Multilingual RAG

Multilingual Retrieval-Augmented Generation (RAG) systems serving low-resource languages can suffer from unintended retrieval bias when language preferences are applied without accounting for the score scale of the underlying fusion method. This paper investigates a failure mode in a trilingual agricultural advisory system, Bhunaga, supporting English, Hindi, and Marathi. The system uses BGE-M3 dense and sparse retrieval combined through Reciprocal Rank Fusion (RRF) with a rank constant of k = 60. We demonstrate that an additive same-language bonus of +0.10 exceeds the maximum attainable fused score range of 0.0217 by approximately 4.6 times, effectively turning a soft reranking preference into a hard language filter. We derive the partition condition mathematically and evaluate three configurations: additive bonus, multiplicative bonus, and no language preference. Experiments on a corpus of 114 chunks across 24 documents show that the additive bonus reduces keyword recall by 45% for Hindi and 39% for Marathi compared with no bonus. English retrieval remains unchanged, acting as an internal control. We also identify a misleading monitoring metric: same-language retrieval rate reaches 1.00 precisely when retrieval quality is at its worst. The study proposes a scale-aware approach to score adjustment, recommends multiplicative adjustments where appropriate, and demonstrates why multilingual retrieval systems should evaluate cross-lingual retrieval quality rather than relying solely on same-language retrieval rates. Keywords: Multilingual RAG, Reciprocal Rank Fusion, Cross-Lingual Retrieval, Information Retrieval, BGE-M3, Score-Scale Mismatch, Natural Language Processing.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24332200
Primary Topic
Information Retrieval and Search Behavior
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

When a Reranking Bonus Becomes a Language Filter: Score-Scale Mismatch in Reciprocal Rank Fusion for Multilingual RAG

Aishwarya Deshmukh, Harshal Punjahari Agre, Jayesh Vilas Kapade, Manish Yadav
1 links
Zenodo (CERN European Organization for Nuclear Research)
Information Retrieval and Search Behavior
preprint

When a Reranking Bonus Becomes a Language Filter: Score-Scale Mismatch in Reciprocal Rank Fusion for Multilingual RAG

Aishwarya Deshmukh, Harshal Punjahari Agre, Jayesh Vilas Kapade, Manish Yadav
preprint en

Abstract

Multilingual Retrieval-Augmented Generation (RAG) systems serving low-resource languages can suffer from unintended retrieval bias when language preferences are applied without accounting for the score scale of the underlying fusion method. This paper investigates a failure mode in a trilingual agricultural advisory system, Bhunaga, supporting English, Hindi, and Marathi. The system uses BGE-M3 dense and sparse retrieval combined through Reciprocal Rank Fusion (RRF) with a rank constant of k = 60. We demonstrate that an additive same-language bonus of +0.10 exceeds the maximum attainable fused score range of 0.0217 by approximately 4.6 times, effectively turning a soft reranking preference into a hard language filter. We derive the partition condition mathematically and evaluate three configurations: additive bonus, multiplicative bonus, and no language preference. Experiments on a corpus of 114 chunks across 24 documents show that the additive bonus reduces keyword recall by 45% for Hindi and 39% for Marathi compared with no bonus. English retrieval remains unchanged, acting as an internal control. We also identify a misleading monitoring metric: same-language retrieval rate reaches 1.00 precisely when retrieval quality is at its worst. The study proposes a scale-aware approach to score adjustment, recommends multiplicative adjustments where appropriate, and demonstrates why multilingual retrieval systems should evaluate cross-lingual retrieval quality rather than relying solely on same-language retrieval rates. Keywords: Multilingual RAG, Reciprocal Rank Fusion, Cross-Lingual Retrieval, Information Retrieval, BGE-M3, Score-Scale Mismatch, Natural Language Processing.

Zenodo (CERN European Organization for Nuclear Research)
MIT Art, Design and Technology University (IN)
Reduced inequalities
Information Retrieval and Search Behavior
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon