The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora

• URL: http://arxiv.org/abs/2507.07543v1
• Date: Thu, 10 Jul 2025 08:38:31 GMT
• Title: The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora
• Authors: Chen Amiraz, Yaroslav Fyodorov, Elad Haramaty, Zohar Karnin, Liane Lewin-Eytan,
• Abstract summary: Cross-lingual retrieval-augmented generation (RAG) is a critical capability for retrieving and generating answers across languages.<n>We study Arabic-English RAG in a domain-specific setting using benchmarks derived from real-world corporate datasets.<n>We propose a simple retrieval strategy that addresses this source of failure by enforcing equal retrieval from both languages.
• Score: 6.594531626178451
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-lingual retrieval-augmented generation (RAG) is a critical capability for retrieving and generating answers across languages. Prior work in this context has mostly focused on generation and relied on benchmarks derived from open-domain sources, most notably Wikipedia. In such settings, retrieval challenges often remain hidden due to language imbalances, overlap with pretraining data, and memorized content. To address this gap, we study Arabic-English RAG in a domain-specific setting using benchmarks derived from real-world corporate datasets. Our benchmarks include all combinations of languages for the user query and the supporting document, drawn independently and uniformly at random. This enables a systematic study of multilingual retrieval behavior. Our findings reveal that retrieval is a critical bottleneck in cross-lingual domain-specific scenarios, with significant performance drops occurring when the user query and supporting document languages differ. A key insight is that these failures stem primarily from the retriever's difficulty in ranking documents across languages. Finally, we propose a simple retrieval strategy that addresses this source of failure by enforcing equal retrieval from both languages, resulting in substantial improvements in cross-lingual and overall performance. These results highlight meaningful opportunities for improving multilingual retrieval, particularly in practical, real-world RAG applications.

Related papers

• CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents [2.0277446818410994]
  This paper presents CLIRudit, a new dataset created to evaluate cross-lingual academic search.<n>The dataset is built using bilingual article metadata from 'Erudit, a Canadian publishing platform.
  arXiv  Detail & Related papers  (2025-04-22T20:55:08Z)
• Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task [73.35882908048423]
  Retrieval-augmented generation (RAG) has become a cornerstone of contemporary NLP.<n>This paper investigates the effectiveness of RAG across multiple languages by proposing novel approaches for multilingual open-domain question-answering.
  arXiv  Detail & Related papers  (2025-04-04T17:35:43Z)
• Investigating Language Preference of Multilingual RAG Systems [4.438698005789677]
  MRAG systems struggle with retrieving relevant information due to linguistic variations between queries and documents.<n>We propose Dual Knowledge Multilingual RAG (DKM-RAG), a framework that fuses translated multilingual passages with complementary model knowledge.<n> Empirical results demonstrate that DKM-RAG mitigates language preference in generation and enhances performance across diverse linguistic settings.
  arXiv  Detail & Related papers  (2025-02-16T15:54:05Z)
• mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval [61.17793165194077]
  We introduce mFollowIR, a benchmark for measuring instruction-following ability in retrieval models.<n>We present results for both multilingual (XX-XX) and cross-lingual (En-XX) performance.<n>We see strong cross-lingual performance with English-based retrievers that trained using instructions, but find a notable drop in performance in the multilingual setting.
  arXiv  Detail & Related papers  (2025-01-31T16:24:46Z)
• Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness [30.00463676754559]
  We introduce BordIRLines, a dataset of territorial disputes paired with retrieved Wikipedia documents, across 49 languages.<n>We evaluate the cross-lingual robustness of this RAG setting by formalizing several modes for multilingual retrieval.<n>Our experiments show that incorporating perspectives from diverse languages can in fact improve robustness.
  arXiv  Detail & Related papers  (2024-10-02T01:59:07Z)
• Cross-lingual Contextualized Phrase Retrieval [63.80154430930898]
  We propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval. We train our Cross-lingual Contextualized Phrase Retriever (CCPR) using contrastive learning. On the phrase retrieval task, CCPR surpasses baselines by a significant margin, achieving a top-1 accuracy that is at least 13 points higher.
  arXiv  Detail & Related papers  (2024-03-25T14:46:51Z)
• CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval [73.48591773882052]
  Most fact-checking approaches focus on English only due to the data scarcity issue in other languages. We present the first fact-checking framework augmented with crosslingual retrieval. We train the retriever with our proposed Crosslingual Inverse Cloze Task (XICT)
  arXiv  Detail & Related papers  (2022-09-05T17:36:14Z)
• On Cross-Lingual Retrieval with Multilingual Text Encoders [51.60862829942932]
  We study the suitability of state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks. We benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR experiments. We evaluate multilingual encoders fine-tuned in a supervised fashion (i.e., we learn to rank) on English relevance data in a series of zero-shot language and domain transfer CLIR experiments.
  arXiv  Detail & Related papers  (2021-12-21T08:10:27Z)
• XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization [98.61159823343036]
  We present the Word-in-Context dataset (WiC) for assessing the ability to correctly model distinct meanings of a word. We put forward a large multilingual benchmark, XL-WiC, featuring gold standards in 12 new languages. Experimental results show that even when no tagged instances are available for a target language, models trained solely on the English data can attain competitive performance.
  arXiv  Detail & Related papers  (2020-10-13T15:32:00Z)
• LAReQA: Language-agnostic answer retrieval from a multilingual pool [29.553907688813347]
  LAReQA tests for "strong" cross-lingual alignment. We find that augmenting training data via machine translation is effective. This finding underscores our claim that languageagnostic retrieval is a substantively new kind of cross-lingual evaluation.
  arXiv  Detail & Related papers  (2020-04-11T20:51:11Z)

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.