---
title: "Why Low-Resource NLP Needs More Than Cross-Lingual"
description: "They offer practical guidelines, such as using high-resource languages as scaffolding. 18 references."
authors: ["Fred Philippy", "Siwen Guo", "Jacques Klein", "Tegawendé F. Bissyandé"]
year: 2026
venue: "Proceedings of The Big Picture v2: Crafting a Research Narrative"
source: "https://aclanthology.org/2026.bigpicture-main.7/"
doi: "10.18653/v1/2026.bigpicture-main.7"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/philippy-2026-why-low-resource-nlp-needs/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/philippy-2026-why-low-resource-nlp-needs/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/56/) / Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish

# Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish

**Authors:** [Fred Philippy](https://md.research.elamur.ai/free/en/authors/fred-philippy/), [Siwen Guo](https://md.research.elamur.ai/free/en/authors/siwen-guo/), [Jacques Klein](https://md.research.elamur.ai/free/en/authors/jacques-klein/) and [Tegawendé F. Bissyandé](https://md.research.elamur.ai/free/en/authors/tegawende-bissyande/) · **Year:** 2026 · **Venue:** [Proceedings of The Big Picture v2: Crafting a Research Narrative](https://md.research.elamur.ai/free/en/venues/bigpicture/) ([Big Picture v2: Crafting a Research Narrative 2026](https://md.research.elamur.ai/free/en/venues/bigpicture/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.bigpicture-main.7/) · [PDF](https://aclanthology.org/2026.bigpicture-main.7.pdf) · [DOI 10.18653/v1/2026.bigpicture-main.7](https://doi.org/10.18653/v1/2026.bigpicture-main.7) · [OpenAlex](https://openalex.org/W7166857715)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary

This position-style paper asks whether cross-lingual transfer from high-resource languages can replace dedicated work on a low-resource language. The authors use Luxembourgish as a test case. It is close to German, borrows heavily from French, uses the Latin script, has official status and institutional backing, and has an unusually large online footprint for its size. They treat it as a near best-case scenario, roughly the ceiling of what transfer can achieve. They draw on their own earlier studies and data-collection efforts and find that current models still underperform on Luxembourgish. Transfer helps a lot, but only when enough clean, task-matched target-language data exists. Poor data quality, mismatched objectives and unreliable evaluation all weaken it. Native resources alone are too small to produce strong models. The authors therefore see the two approaches as complementary parts of one development cycle. They offer practical guidelines, such as using high-resource languages as scaffolding. This matters because languages that are more distant or marginalized will likely face even larger gaps if transfer falls short here.

## Key points

- Luxembourgish has about 400,000 speakers. Most of them also speak French, German or English, often at near-native level, and code-switching is common.
- In a PCA projection of syntactic, phonological, inventory, genetic and geographic features, Luxembourgish falls inside a dense cluster of mostly mid- to high-resource languages. Wikipedia article counts serve as the resource proxy.
- Curated institutional resources exist, including official orthography guidelines and dictionary data from the Zenter fir d'Lëtzebuerger Sprooch (lod.lu).
- The authors criticize the view that transfer simply "emerges" from multilingual pretraining, citing the Qwen-3 report. Methods such as alignment, adapters and continued pre-training quietly assume good target-language resources.
- The authors admit the "upper bound" framing is a theoretical approximation rather than a validated claim. Note: the provided extract omits the paper's middle sections, so specific experimental figures are not covered here.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Luxembourg](https://md.research.elamur.ai/free/en/universities/university-of-luxembourg/) — University, Luxembourg, Luxembourg · 28 works · 337 citations
- [Luxembourg Institute of Science and Technology](https://md.research.elamur.ai/free/en/labs/luxembourg-institute-of-science-and-technology/) — Research institute, Belvaux, Luxembourg · 6 works · 9 citations
- [Interdisciplinary Centre for Security, Reliability and Trust](https://md.research.elamur.ai/free/en/universities/interdisciplinary-centre-for-security-reliability-and-trust/) — University, Belval, Luxembourg · 3 works · 3 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (2): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works · [🌱 Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · 287 works

## Cite

Cite as: Fred Philippy, Siwen Guo, Jacques Klein and Tegawendé F. Bissyandé. 2026. Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish. Proceedings of The Big Picture v2: Crafting a Research Narrative.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{philippy2026why,
  title = {{Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish}},
  author = {Fred Philippy, Siwen Guo, Jacques Klein and Tegawendé F. Bissyandé},
  booktitle = {Proceedings of The Big Picture v2: Crafting a Research Narrative},
  year = {2026},
  doi = {10.18653/v1/2026.bigpicture-main.7},
  url = {https://doi.org/10.18653/v1/2026.bigpicture-main.7}
}
```

- [← previous Why LoRA Fails to Forget: Regularized Low-Rank Adaptation Against Backdoors in Language Models](https://md.research.elamur.ai/free/en/papers/luong-2026-why-lora-fails-forget-regularized/)
- [next → Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks](https://md.research.elamur.ai/free/en/papers/wang-2026-why-multimodal-context-learning-lags/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/56/)

## References

18 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdullatif Köksal, Marion Thaler, Ayyoob Imani, Ahmet Üstün, Anna Korhonen, and Hinrich Schütze. 2025. Muri: High-quality instruction tuning datasets for low-resource languages via reverse instructions. Transactions of the Association for Computational Linguistics, 13:1032–1055. [↗](https://doi.org/10.1162/tacl.a.18)
2. Pinzhen Chen, Shaoxiong Ji, Nikolay Bogoychev, Andrey Kutuzov, Barry Haddow, and Kenneth Heafield. 2024. Monolingual or multilingual instruction tuning: Which makes a better alpaca. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1347–1356, St. Julian’s, Malta. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Pinzhen+Chen%2C+Shaoxiong+Ji%2C+Nikolay+Bogoychev%2C+Andrey+Kutuzov%2C+Barry+Haddow%2C+and+Kenneth+Heafield%2E+2024%2E+Monolingual+or+multilingual+instruction+tuning%3A+Which+makes+a+better+alpaca%2E+In+Findings+of+the)
3. Chong Li, Wen Yang, Jiajun Zhang, Jinliang Lu, Shaonan Wang, and Chengqing Zong. 2024. X-instruction: Aligning language model in low-resource languages with self-curated cross-lingual instructions. In Findings of the Association for Computational Linguistics: ACL 2024, pages 546–566, Conseil fir d’Lëtzebuerger Sprooch and Zenter fir d’Lëtzebuerger Sprooch. 2019. D’Lëtzebuerger Orthografie, 6 edition. Ministère fir Educatioun, Kanner a Jugend, Lëtzebuerg. Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chong+Li%2C+Wen+Yang%2C+Jiajun+Zhang%2C+Jinliang+Lu%2C+Shaonan+Wang%2C+and+Chengqing+Zong%2E+2024%2E+X%2Dinstruction%3A+Aligning+language+model+in+low%2Dresource+languages+with+self%2Dcurated+cross%2Dlingual+instructions%2E+In)
4. Fred Philippy, Siwen Guo, and Shohreh Haddadan. 2023. Towards a common understanding of contributing factors for cross-lingual transfer in multilingual language models: A review. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5877–5891, Toronto, Canada. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Fred+Philippy%2C+Siwen+Guo%2C+and+Shohreh+Haddadan%2E+2023%2E+Towards+a+common+understanding+of+contributing+factors+for+cross%2Dlingual+transfer+in+multilingual+language+models%3A+A+review%2E+In+Proceedings+of+the)
5. Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O’Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, and 2 others. 2022. [Few-shot learning with multilingual generative language models](https://md.research.elamur.ai/free/en/papers/lin-2021-few-shot-learning-multilingual-language/). In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9019–9052, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
6. Fred Philippy, Siwen Guo, Jacques Klein, and Tegawende Bissyande. 2025b. [LuxEmbedder: A cross-lingual approach to enhanced Luxembourgish sentence embeddings](https://md.research.elamur.ai/free/en/papers/philippy-2025-luxembedder-cross-lingual-approach-enhanced/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 11369–11379, Abu Dhabi, UAE. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2412.03331)
7. Patrick Littell, David R. Mortensen, Ke Lin, Katherine Kairis, Carlisle Turner, and Lori Levin. 2017. [URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors](https://md.research.elamur.ai/free/en/papers/littell-2017-uriel-lang2vec-representing-languages-as/). In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 8–14, Valencia, Spain. Association for Computational Linguistics.
8. Fred Philippy, Shohreh Haddadan, and Siwen Guo. 2024. Forget NLI, use a dictionary: Zero-shot topic classification for low-resource languages with application to Luxembourgish. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024, pages 97–104, Torino, Italia. ELRA and ICCL. [find](https://scholar.google.com/scholar?q=Fred+Philippy%2C+Shohreh+Haddadan%2C+and+Siwen+Guo%2E+2024%2E+Forget+NLI%2C+use+a+dictionary%3A+Zero%2Dshot+topic+classification+for+low%2Dresource+languages+with+application+to+Luxembourgish%2E+In+Proceedings+of+the+3)
9. Alistair Plum, Caroline Döhmer, Emilia Milano, Anne-Marie Lutgen, and Christoph Purschke. 2024. LuxBank: The first Universal Dependency treebank for Luxembourgish. In Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024), pages 30–39, Hamburg,Germany. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2411.04813)
10. Le Liu, Yu Hong, Jun Lu, Jun Lang, Heng Ji, and Jianmin Yao. 2014. An iterative link-based method for parallel web page mining. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1216–1224, Doha, Qatar. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Le+Liu%2C+Yu+Hong%2C+Jun+Lu%2C+Jun+Lang%2C+Heng+Ji%2C+and+Jianmin+Yao%2E+2014%2E+An+iterative+link%2Dbased+method+for+parallel+web+page+mining%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+La)
11. Dan Malkin, Tomasz Limisiewicz, and Gabriel Stanovsky. 2022. A balanced data approach for evaluating cross-lingual transfer: Mapping the linguistic blood bank. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4903–4915, Seattle, United States. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dan+Malkin%2C+Tomasz+Limisiewicz%2C+and+Gabriel+Stanovsky%2E+2022%2E+A+balanced+data+approach+for+evaluating+cross%2Dlingual+transfer%3A+Mapping+the+linguistic+blood+bank%2E+In+Proceedings+of+the+2022+Conference+of)
12. Surangika Ranathunga, Nisansa de Silva, Menan Velayuthan, Aloka Fernando, and Charitha Rathnayake. 2024. Quality does matter: A detailed look at the quality and utility of web-mined parallel corpora. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 860–880, St. Julian’s, Malta. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2402.07446)
13. Marinela Parović, Goran Glavaš, Ivan Vulić, and Anna Korhonen. 2022. BAD-X: Bilingual adapters improve zero-shot cross-lingual transfer. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1791–1799, Seattle, United States. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Marinela+Parovic%CC%81%2C+Goran+Glava%C5%A1%2C+Ivan+Vulic%CC%81%2C+and+Anna+Korhonen%2E+2022%2E+BAD%2DX%3A+Bilingual+adapters+improve+zero%2Dshot+cross%2Dlingual+transfer%2E+In+Proceedings+of+the+2022+Conference+of+the+North+American+C)
14. Sandy Ritchie, Daan van Esch, Uche Okonkwo, Shikhar Vashishth, and Emily Drummond. 2024. LinguaMeta: Unified metadata for thousands of languages. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10530–10538, Torino, Italia. ELRA and ICCL. [find](https://scholar.google.com/scholar?q=Sandy+Ritchie%2C+Daan+van+Esch%2C+Uche+Okonkwo%2C+Shikhar+Vashishth%2C+and+Emily+Drummond%2E+2024%2E+LinguaMeta%3A+Unified+metadata+for+thousands+of+languages%2E+In+Proceedings+of+the+2024+Joint+International+Confere)
15. Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, and Sebastian Ruder. 2020. [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://md.research.elamur.ai/free/en/papers/pfeiffer-2020-mad-x-adapter-based-framework/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7654–7673, Online. Association for Computational Linguistics.
16. Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong, and Francisco Guzmán. 2021a. Wiki-Matrix: Mining 135M parallel sentences in 1620 language pairs from Wikipedia. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1351–1361, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Holger+Schwenk%2C+Vishrav+Chaudhary%2C+Shuo+Sun%2C+Hongyu+Gong%2C+and+Francisco+Guzm%C3%A1n%2E+2021a%2E+Wiki%2DMatrix%3A+Mining+135M+parallel+sentences+in+1620+language+pairs+from+Wikipedia%2E+In+Proceedings+of+the+16th+Con)
17. Fred Philippy, Laura Bernardy, Siwen Guo, Jacques Klein, and Tegawendé F. Bissyandé. 2025a. [Luxin-struct: A cross-lingual instruction tuning dataset for luxembourgish](https://md.research.elamur.ai/free/en/papers/philippy-2025-luxinstruct-cross-lingual-instruction-tuning/). Preprint, arXiv:2510.07074. [↗](https://arxiv.org/abs/2510.07074)
18. Holger Schwenk, Guillaume Wenzek, Sergey Edunov, Edouard Grave, Armand Joulin, and Angela Fan. 2021b. [CCMatrix: Mining billions of high-quality parallel sentences on the web](https://md.research.elamur.ai/free/en/papers/schwenk-2019-ccmatrix-mining-billions-high-quality/). In Proceedings of the

*Updated 1 November 2026*