Cross-modal augmentation for low-resource language understanding and generation
Open accessAbstract
This paper introduces a multimodal retrievalaugmented generation (RAG) system designed to enhance language understanding and generation for low-resource languages.By integrating textual, visual, and geospatial data, the system leverages cross-lingual adaptation and multimodal augmentation to bridge the gap between high-resource and low-resource languages.Evaluated on the MM-COVID and LORELEI datasets, the system demonstrates superior performance in retrieval (precision: 85%, recall: 82%) and generation (BLEU: 28.4) tasks compared to baselines.Case studies in public health communication and disaster response highlight its practical utility.The results underscore the potential of multimodal AI to democratize access to technology and address global challenges in low-resource settings.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Extending RAG to low-resource languages presents unique challenges, primarily due to weak embedding representations and a lack of digitized corpora.
“Extending RAG to low-resource languages presents unique challenges, primarily due to weak embedding representations and a lack of digitized corpora (Li and Ke, 2025).”
From Improving Amharic Information Retrieval with Translative and Multi-Agent Debate Retrieval Augmented Generation (2026) · cites this paper as Li and Ke, 2025
Cites
Still being checked.
Cited by
Sorted by citations
Du, C., Chiang, C.-E., Huang, T., & Cui, Z. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290280 · Cited by 1 · see citing works
Fan, Z., Fan, P., & Wang, Y. (2026) · Systems · doi:10.3390/systems14030319 · Cited by 1 · see citing works
Jotie, A. A., & Mitra, P. (2026) · Proceedings of the Language Resources and Evaluation Conference · doi:10.63317/3hbm9z4okcrx
Training Strategies for Speech Large Language Models: A Comprehensive Survey
Yang, S., Huang, Z., & Xiao, W. (2025) · International Conference on Foundation and Large Language Models (FLLM) · doi:10.1109/fllm67465.2025.11391055
Utami, E., Wahyuni, S. N., Sulistiyono, M., Raharjo, S., Hartanto, A. D., Rohman, A. N., Triwijoyo, B. K., Miswaty, T. C., Patty, E. N. S., & Fahry (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.17086
ParCoder: Harnessing Transformer Models for Parallel Code Generation with OpenMP and MPI
Chen, L., Arijit, A., Ahmed, N., Hasabnis, N., Capotă, M., Munoz, P., Oren, G., Vo, V., Chapman, B., & Jannesari, A. (2026) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw71298.2026.00034
- Authors
- Li, Z., & Ke, Z.
- Affiliations
- National University of Singapore (SG)
- ORCID
- Venue
- Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)
- Published
- 2025
- Pages
- 90-99
- OpenAlex
- W4412944325
- Cited by
- 5
- References
- 0
- Citations by year
- 2026: 3 · 2025: 2
- FWCI
- 3.75
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- low-resource languages, language comprehension, language generation, multilingual NLP
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
