---
title: "Dallah — paper by Alwajih et al. (2024) — summary and ideas"
description: "To build training data, the authors machine-translated English visual instruction sets into Modern… 41 references, cited by 13 papers here."
authors: ["Fakhraddin Alwajih", "Gagan Bhatia", "Muhammad Abdul-Mageed"]
year: 2024
venue: "Proceedings of the Second Arabic Natural Language Processing Conference"
source: "https://aclanthology.org/2024.arabicnlp-1.27/"
doi: "10.18653/v1/2024.arabicnlp-1.27"
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/alwajih-2024-dallah-dialect-aware-multimodal-large/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/alwajih-2024-dallah-dialect-aware-multimodal-large/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/7/) / Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic

# Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic

**Authors:** [Fakhraddin Alwajih](https://md.research.elamur.ai/free/en/authors/fakhraddin-alwajih/), [Gagan Bhatia](https://md.research.elamur.ai/free/en/authors/gagan-bhatia/) and [Muhammad Abdul-Mageed](https://md.research.elamur.ai/free/en/authors/muhammad-abdul-mageed/) · **Year:** 2024 · **Venue:** [Proceedings of the Second Arabic Natural Language Processing Conference](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2024](https://md.research.elamur.ai/free/en/venues/arabicnlp/2024/)) · **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/2024.arabicnlp-1.27/) · [PDF](https://aclanthology.org/2024.arabicnlp-1.27.pdf) · [DOI 10.18653/v1/2024.arabicnlp-1.27](https://doi.org/10.18653/v1/2024.arabicnlp-1.27) · [OpenAlex](https://openalex.org/W4402671446)

**Citations:** 12 citations (OpenAlex, 2026-10-14) · [13](https://md.research.elamur.ai/free/en/papers/alwajih-2024-dallah-dialect-aware-multimodal-large/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Multimodal LLMs that can discuss images are mostly built for English. Arabic has few image-text resources, and Arabic's regional dialects have almost none. Dallah addresses this gap. It joins the LLaVA framework with AraLLaMA, a LLaMA-2-based model that handles both Arabic and English.

To build training data, the authors machine-translated English visual instruction sets into Modern Standard Arabic (MSA). They then back-translated each item and kept it only if its question and answer stayed close to the English original under a strong sentence-embedding model.

For dialect support, native professional translators rewrote small, varied MSA subsets into six dialects. The authors also released Dallah-Bench, which scores dialect responses on two separate axes: how authentic the dialect is and how accurate the content is. They compared several LLM judges against human raters on this benchmark.

Dallah reaches state-of-the-art results among Arabic multimodal models on the LLaVA-benchmark. It answers in dialect, whereas GPT-4V kept replying in MSA. The work shows a practical recipe for adding dialect awareness with limited data.

## Key points
- The architecture is LLaVA (vision encoder plus projection) with AraLLaMA as the language backbone.
- The translate-and-filter pipeline works in three steps:
  - It translates with the Google Translate API and then back-translates.
  - It measures embedding similarity using an English embedding model based on Mistral-7b, which was chosen for its MTEB standing.
  - It discards pairs that fall below a threshold of 0.8 (80%).
- The six dialects in the data are those of Yemen, Morocco, Egypt, Palestine, Mauritania, and Saudi Arabia. It was drawn from random subsets of the translated LLaVA-instruct 150k, mixing conversation, complex reasoning, and detailed description.
- Dallah-Bench uses two scores, Dialect Authenticity and Context Accuracy, each with a written reason. The LLM judges compared were GPT4, GPT4-Turbo, and Command-R+, and Command R+ tracked human dialect judgments most closely.
- The authors list several limitations:
  - The model confuses close dialects, such as Yemeni and Saudi.
  - It struggles with dialects that are near MSA.
  - It cannot read Arabic text inside images.
  - It recognizes Arab public figures poorly.

## Interesting ideas
- Filtering machine-translated data by round-trip translation plus embedding similarity catches silent meaning drift, such as "surfers" becoming "browser," without needing a human.
- A small, professionally produced variety-specific sample, deliberately mixed across content types, can be enough to teach a model a new variety.
- Scoring outputs on two independent axes, form (dialect authenticity) and substance (content accuracy), each with a justification, makes failures easier to diagnose than a single score.
- Before trusting LLM judges, the authors compared several of them against human raters and picked the one that matched humans best. Humans remain the reference wherever cultural nuance matters.
- The paper observes that written dialect looks closer to the standard language than spoken dialect does, which can bias raters. Evaluation should account for how the modality of presentation affects judgment.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (back): The text → graph → text compressor could use the same round-trip test, keeping a generated sentence only if re-parsing it gives a graph close to the source.
- **I2** (tree): When adding a new UD dialect conversion, a compact gold set balanced across genres could validate the converted treebank before scaling up.
- **I3** (answer): Reader evaluations could grade answer correctness separately from surface fluency or format, with a stated reason for each grade.
- **I4** (learn): LLM teacher tiers could each be calibrated on a human-checked slice, and the agreement rate could decide which teacher is trusted for which phenomenon.
- **I5** (learn): Negative controls in evaluation could check whether rater or teacher verdicts change merely with how a text is presented, not with what it says.

*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 British Columbia](https://md.research.elamur.ai/free/en/universities/university-of-british-columbia/) — University, Vancouver, Canada · 98 works · 34,805 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: Fakhraddin Alwajih, Gagan Bhatia and Muhammad Abdul-Mageed. 2024. Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic. Proceedings of the Second Arabic Natural Language Processing Conference.

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

```bibtex
@inproceedings{alwajih2024dallah,
  title = {{Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic}},
  author = {Fakhraddin Alwajih, Gagan Bhatia and Muhammad Abdul-Mageed},
  booktitle = {Proceedings of the Second Arabic Natural Language Processing Conference},
  year = {2024},
  doi = {10.18653/v1/2024.arabicnlp-1.27},
  url = {https://doi.org/10.18653/v1/2024.arabicnlp-1.27}
}
```

- [← previous The FIGNEWS Shared Task on News Media Narratives](https://md.research.elamur.ai/free/en/papers/zaghouani-2024-fignews-shared-task-news-media/)
- [next → Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://md.research.elamur.ai/free/en/papers/sun-2024-hunyuan-large-open-source/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/7/)

## References

41 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, et al. 2024. [Phi-3 technical report: A highly capable language model locally on your phone](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-3-technical-report-highly/). arXiv preprint arXiv:2404.14219. [↗](https://arxiv.org/abs/2404.14219)
2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774. [↗](https://arxiv.org/abs/2303.08774)
3. Azimjon Ahmedov and Xabibullayeva Shaxrizoda. 2024. The english effect. Ta’limning zamonaviy transformatsiyasi, 7(3):18–23. [find](https://scholar.google.com/scholar?q=Azimjon+Ahmedov+and+Xabibullayeva+Shaxrizoda%2E+2024%2E+The+english+effect%2E+Ta%E2%80%99limning+zamonaviy+transformatsiyasi%2C+7%283%29%3A18%E2%80%9323%2E)
4. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. [Flamingo: a visual language model for few-shot learning](https://md.research.elamur.ai/free/en/papers/alayrac-2022-flamingo-visual-language-model-few/). Advances in neural information processing systems, 35:23716–23736. [↗](https://doi.org/10.48550/arxiv.2204.14198)
5. Fakhraddin Alwajih, El Moatez Billah Nagoudi, Gagan Bhatia, Abdelrahman Mohamed, and Muhammad Abdul-Mageed. 2024. [Peacock: A family of arabic multimodal large language models and benchmarks](https://md.research.elamur.ai/free/en/papers/alwajih-2024-peacock-family-arabic-multimodal-large/). Preprint, arXiv:2403.01031. [↗](https://arxiv.org/abs/2403.01031)
6. Richard Barnet and John Cavanagh. 2014. Homogenization of global culture. In The case against the global economy, pages 169–174. Routledge. [find](https://scholar.google.com/scholar?q=Richard+Barnet+and+John+Cavanagh%2E+2014%2E+Homogenization+of+global+culture%2E+In+The+case+against+the+global+economy%2C+pages+169%E2%80%93174%2E+Routledge%2E)
7. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
8. Guiming Hardy Chen, Shunian Chen, Ruifei Zhang, Junying Chen, Xiangbo Wu, Zhiyi Zhang, Zhihong Chen, Jianquan Li, Xiang Wan, and Benyou Wang. 2024. [Allava: Harnessing gpt4v-synthesized data for a lite vision-language model](https://md.research.elamur.ai/free/en/papers/chen-2024-allava-harnessing-gpt4v-synthesized-data/). arXiv preprint arXiv:2402.11684. [↗](https://arxiv.org/abs/2402.11684)
9. Lin Chen, Jisong Li, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, and Dahua Lin. 2023. [Sharegpt4v: Improving large multimodal models with better captions](https://md.research.elamur.ai/free/en/papers/chen-2023-sharegpt4v-improving-large-multi-modal/). arXiv preprint arXiv:2311.12793. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan https://alliancecan.ca [↗](https://arxiv.org/abs/2311.12793)
10. Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. [find](https://scholar.google.com/scholar?q=Zhuang%2C+Yonghao+Zhuang%2C+Joseph+E%2E+Gonzalez%2C+Ion+Stoica%2C+and+Eric+P%2E+Xing%2E+2023%2E+Vicuna%3A+An+open%2Dsource+chatbot+impressing+gpt%2D4+with+90%25%2A+chatgpt+quality%2E)
11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). arXiv preprint arXiv:1810.04805. [↗](https://arxiv.org/abs/1810.04805)
12. Zakaria Fahmi and Dacota Liska. 2024. Promoting arabic as a foreign language in the middle east and north africa: Host-grounded study abroad discourses. Frontiers: The Interdisciplinary Journal of Study Abroad, 36(1):384–417. [↗](https://doi.org/10.36366/frontiers.v36i1.792)
13. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). arXiv preprint arXiv:2106.09685. [↗](https://arxiv.org/abs/2106.09685)
14. Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Dingjie Song, Zhihong Chen, Abdulmohsen Alharthi, Bang An, Ziche Liu, Zhiyi Zhang, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, and Jinchao Xu. 2023. [Acegpt, localizing large language models in arabic](https://md.research.elamur.ai/free/en/papers/huang-2024-acegpt-localizing-large-language-models/). Preprint, arXiv:2309.12053. [↗](https://arxiv.org/abs/2309.12053)
15. Mojan Javaheripi, Sébastien Bubeck, Marah Abdin, Jyoti Aneja, Caio César Teodoro Mendes, Weizhu Chen, Allie Del Giorno, Ronen Eldan, Sivakanth Gopi, Suriya Gunasekar, Piero Kauffmann, Yin Tat Lee, Yuanzhi Li, Anh Nguyen, Gustavo de Rosa, Olli Saarikivi, Adil Salim, Shital Shah, Michael Santacroce, Harkirat Singh Behl, Adam Taumann Kalai, Xin Wang, Rachel Ward, Philipp Witte, Cyril Zhang, and Yi Zhang. 2023. Phi-2: The surprising power of small language models. Microsoft Research Blog. [find](https://scholar.google.com/scholar?q=Mojan+Javaheripi%2C+S%C3%A9bastien+Bubeck%2C+Marah+Abdin%2C+Jyoti+Aneja%2C+Caio+C%C3%A9sar+Teodoro+Mendes%2C+Weizhu+Chen%2C+Allie+Del+Giorno%2C+Ronen+Eldan%2C+Sivakanth+Gopi%2C+Suriya+Gunasekar%2C+Piero+Kauffmann%2C+Yin+Tat+Lee%2C+Yua)
16. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. [↗](https://arxiv.org/abs/2310.06825)
17. Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088. [↗](https://arxiv.org/abs/2401.04088)
18. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. [Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models](https://md.research.elamur.ai/free/en/papers/li-2023-blip-2-bootstrapping-language-image/). In International conference on machine learning, pages 19730–19742. PMLR. [↗](https://doi.org/10.48550/arxiv.2301.12597)
19. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. [Microsoft coco: Common objects in context](https://md.research.elamur.ai/free/en/papers/lin-2014-microsoft-coco-common-objects-context/). In Computer Vision– ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer. [↗](https://doi.org/10.4230/lipics.cosit.2024.1)
20. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023a. [Improved baselines with visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-improved-baselines-visual-instruction-tuning/).
21. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024. [Improved baselines with visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-improved-baselines-visual-instruction-tuning/). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 26296–26306.
22. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. [Visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-visual-instruction-tuning/). In NeurIPS. [↗](https://doi.org/10.48550/arxiv.2304.08485)
23. Muhammad Maaz, Hanoona Rasheed, Abdelrahman Shaker, Salman Khan, Hisham Cholakal, Rao M. Anwer, Tim Baldwin, Michael Felsberg, and Fahad S. Khan. 2024. Palo: A polyglot large multimodal model for 5b people. Preprint, arXiv:2402.14818. [↗](https://arxiv.org/abs/2402.14818)
24. Rui Meng, Ye Liu, Shafiq Rayhan Joty, Caiming Xiong, Yingbo Zhou, and Semih Yavuz. 2024. Sfr-embedding-mistral:enhance text retrieval with transfer learning. [find](https://scholar.google.com/scholar?q=Rui+Meng%2C+Ye+Liu%2C+Shafiq+Rayhan+Joty%2C+Caiming+Xiong%2C+Yingbo+Zhou%2C+and+Semih+Yavuz%2E+2024%2E+Sfr%2Dembedding%2Dmistral%3Aenhance+text+retrieval+with+transfer+learning%2E)
25. Abdelrahman Mohamed, Fakhraddin Alwajih, El Moatez Billah Nagoudi, Alcides Inciarte, and Muhammad Abdul-Mageed. 2023. [Violet: A vision-language model for Arabic image captioning with gemini decoder](https://md.research.elamur.ai/free/en/papers/mohamed-2023-violet-vision-language-model-arabic/). In Proceedings of ArabicNLP 2023, pages 1–11, Singapore (Hybrid). Association for Computational Linguistics.
26. Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al. 2022. [Laion-5b: An open large-scale dataset for training next generation image-text models](https://md.research.elamur.ai/free/en/papers/schuhmann-2022-laion-5b-open-large-scale/). Advances in Neural Information Processing Systems, 35:25278–25294. [↗](https://doi.org/10.34734/fzj-2024-00372)
27. Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, Satheesh Katipomu, Haonan Li, Fajri Koto, William Marshall, Gurpreet Gosal, Cynthia Liu, Zhiming Chen, Osama Mohammed Afzal, Samta Kamboj, Onkar Pandit, Rahul Pal, Lalit Pradhan, Zain Muhammad Mujahid, Massa Baali, Xudong Han, Sondos Mahmoud Bsharat, Alham Fikri Aji, Zhiqiang Shen, Zhengzhong Liu, Natalia Vassilieva, Joel Hestness, Andy Hock, Andrew Feldman, Jonathan Lee, Andrew Jackson, Hector Xuguang Ren, Preslav Nakov, Timothy Baldwin, and Eric Xing. 2023. [Jais and jais-chat: Arabic-centric foundation and instruction-tuned open generative large language models](https://md.research.elamur.ai/free/en/papers/sengupta-2023-jais-jais-chat-arabic-centric/). Preprint, arXiv:2308.16149. [↗](https://arxiv.org/abs/2308.16149)
28. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford alpaca: An instruction-following llama model. [https://github.com/tatsu-lab/stanford_alpaca](https://github.com/tatsu-lab/stanford_alpaca). [↗](https://github.com/tatsu-lab/stanford_alpaca)
29. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023a. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971. [↗](https://arxiv.org/abs/2302.13971)
30. Niklas Muennighoff, Nouamane Tazi, Loïc Magne, and Nils Reimers. 2022. [Mteb: Massive text embedding benchmark](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-mteb-massive-text-embedding-benchmark/). arXiv preprint arXiv:2210.07316. [↗](https://arxiv.org/abs/2210.07316)
31. El Moatez Billah Nagoudi, Muhammad Abdul-Mageed, AbdelRahim Elmadany, Alcides Alcoba Inciarte, and Md Tawkat Islam Khondaker. 2023. [Jasmine: Arabic gpt models for few-shot learning](https://md.research.elamur.ai/free/en/papers/nagoudi-2023-jasmine-arabic-gpt-models-few/). Preprint, arXiv:2212.10755. [↗](https://arxiv.org/abs/2212.10755)
32. OpenAI. 2023. Chatgpt. AI language model. Accessed: 2024-04-30. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2023%2E+Chatgpt%2E+AI+language+model%2E+Accessed%3A+2024%2D04%2D30%2E)
33. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International conference on machine learning, pages 8748–8763. PMLR. [↗](https://doi.org/10.48550/arxiv.2103.00020)
34. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+et+al%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
35. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of machine learning research, 21(140):1–67. [↗](https://doi.org/10.48550/arxiv.1910.10683)
36. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023b. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288. [↗](https://arxiv.org/abs/2307.09288)
37. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). Advances in neural information processing systems, 30.
38. Junke Wang, Lingchen Meng, Zejia Weng, Bo He, Zuxuan Wu, and Yu-Gang Jiang. 2023. To see is to believe: Prompting gpt-4v for better visual instruction tuning. arXiv preprint arXiv:2311.07574. [↗](https://arxiv.org/abs/2311.07574)
39. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024. [Multilingual e5 text embeddings: A technical report](https://md.research.elamur.ai/free/en/papers/wang-2024-multilingual-e5-text-embeddings-technical/). Preprint, arXiv:2402.05672. [↗](https://arxiv.org/abs/2402.05672)
40. Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. [Opt: Open pre-trained transformer language models](https://md.research.elamur.ai/free/en/papers/zhang-2022-opt-open-pre-trained-transformer/). arXiv preprint arXiv:2205.01068. [↗](https://arxiv.org/abs/2205.01068)
41. Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, and Lei Li. 2023. [Multilingual machine translation with large language models: Empirical results and analysis](https://md.research.elamur.ai/free/en/papers/zhu-2024-multilingual-machine-translation-large-language/). Preprint, arXiv:2304.04675. [↗](https://arxiv.org/abs/2304.04675)

*Updated 1 November 2026*