Cross-Lingual Information Retrieval for Indonesian–Javanese Documents Using LLM-Based Reranking

Query Translation vs. Cross-Lingual Embeddings for Sinhala-Tamil E-Government Information Retrieval

This paper presents a comparative evaluation of cross-lingual information retrieval (CLIR) methods for retrieving English government information using Sinhala and Tamil queries. Two CLIR paradigms are investigated: Query Translation (QT), employing Google Translate, NLLB, and mBART50, and Cross-Lingual Embeddings (CLE), using LaBSE, multilingual E5, and BGE-M3, with monolingual English retrieval as the baseline. Experiments are conducted on a human-verified benchmark comprising 500 Sinhala, Tamil, and English question-answer pairs derived from 1,699 segmented contexts from Sri Lanka's Government Information Center (GIC). Retrieval performance is evaluated using Recall@k (k = 1, 3, 5, 10, 15). Monolingual retrieval performs poorly (Recall@15<10%), whereas all CLIR approaches substantially improve retrieval accuracy. Among them, BGE-M3 achieves the highest Recall@15, reaching 96.2% for Sinhala-English and 95.6% for Tamil-English, outperforming the best QT approach (Google Translate: 92.4% and 93.0%) while avoiding translation overhead. These results demonstrate that multilingual embedding models provide a more effective and scalable solution for cross-lingual retrieval-augmented generation (RAG) in low-resource government domains.

From Translation to Retrieval: Evaluating LLM-Based Information Retrieval for Hausa and Fongbe

LLM-based reranking has been evaluated for some African languages, but whether LLM-based query expansion helps or hurts retrieval for low-resource African languages remains an open question. Adeyemi et al. evaluated cross-lingual LLM reranking for Hausa with English queries, yet to our knowledge no published work has evaluated LLM-based query expansion for Hausa or Fongbe specifically, and no IR evaluation resources were found for Fongbe. This study builds upon our prior work on LLM translation quality evaluation and data augmentation for corpus expansion in Hausa and Fongbe. We propose experiments that compare LLM reranking and query expansion against BM25 and multilingual dense retrieval baselines (mDPR, mContriever) for Hausa and Fongbe using three commercial LLMs. Our completed translation quality assessment confirms a large LLM-capability gap between the two languages (best BLEU: Hausa 15.75 vs. Fongbe 7.18; human scores 4.5/5 vs. 2.2/5), and our data augmentation experiments across three encoder models show that LLM-generated text consistently hurts downstream NER tasks while producing mixed effects on POS tagging, motivating careful language-specific IR evaluation. We plan to use the CIRAL test collection for Hausa and to construct a new cross-lingual test set derived from Fongbe Wikipedia data following the AfriCLIRMatrix methodology.

DocuMind: An Offline Multilingual Retrieval-Augmented Generation System for Document Question Answering Using Local Large Language Models

DocuMind is a fully offline, privacy-preserving, multilingual Document Question Answering system built on the Retrieval-Augmented Generation (RAG) architecture, enabling true cross-lingual retrieval without any translation step.

Optimising Retrieval for Linguistic Question-Answering in European Portuguese: A Benchmark on Ciberdúvidas Da Língua Portuguesa

A novel benchmark framework for linguistic QA retrieval, empirical evidence supporting monolingual IR-specialised models, and insights into retrieval robustness under paraphrastic variation are included, enabling improved QA systems for specialised and low-resource environments.

Benchmarking and AI-assisted human-like evaluation of retrieval-augmented generation for Arabic and English documents

AraBERT-Based Semantic Lexicon Induction for Arabic Academic Text: Query Expansion, Document Clustering, and Classification

The scarcity of high-quality semantic lexical resources for Arabic academic text represents a critical bottleneck for natural language processing (NLP) applications, including query expansion, document retrieval, and information organization. This paper presents a framework for inducing semantic neighbor lexicons from the Arabic Research Papers Dataset (ARPD), a publicly available corpus of 2,011 Arabic academic documents spanning seven scientific domains. We exploit type-level representations derived from AraBERT to compute dense, L2-normalized word embeddings and apply GPU-accelerated cosine similarity search to retrieve up to three semantically induced neighbors per vocabulary item. Experiments are conducted on both the raw and preprocessed versions of ARPD. The raw-corpus lexicon covers 168,866 unique terms, and the preprocessed-corpus lexicon covers 159,364, both with 100% three-neighbor coverage and a mean top-1 cosine similarity of 0.91. For document clustering, replacing TF-IDF bag-of-words with AraBERT document embeddings raises the Silhouette coefficient from 0.070 to 0.645 on the raw corpus (+ 820.0%) and to 0.755 on the preprocessed corpus (+ 963.4%), alongside substantial reductions in the Davies–Bouldin index. A pilot expansion experiment under class-based relevance finds no retrieval gain from lexicon expansion, which we report alongside the root-level and expert analyses that explain it. For classification, TF-IDF with only light normalization achieves 99.17% accuracy, exceeding the published benchmark of 99.00% that required heavy preprocessing. Comprehensive comparisons against static embedding baselines (Word2Vec, FastText, GloVe) under both corpus conditions quantify how preprocessing depth interacts with representation type. A comparison against MARBERTv2, AraELECTRA, and CAMeLBERT-MSA under leakage-free, validation-based checkpoint selection shows MARBERTv2 attaining the highest accuracy (99.67% raw, 99.50% preprocessed); we emphasize that differences among the top-performing methods correspond to only a few documents and are not statistically significant, while semantic-neighbor augmentation yields a nominal + 1.82 pp gain for AraBERT on the preprocessed corpus (McNemar $p=0.027$ ).