Elamur Research⌕
☰
home / papers / 2024 / LLMs Are Few-Shot In-Context Low-Resource Language Learners

LLMs Are Few-Shot In-Context Low-Resource Language Learners

Paper · 2024 · Samuel Cahyawijaya, Holy Lovenia and Pascale Fung

Summary

Large language models handle low-resource languages poorly, and adapting them through fine-tuning or adapters is expensive and can cause catastrophic forgetting. This paper asks how far in-context learning (ICL) and its cross-lingual form (X-ICL) can help without any parameter updates. Earlier work tested this mainly on well-resourced languages such as French or Spanish. The authors instead run a broad comparison over 25 low-resource and 7 higher-resource languages.

They vary four parts of the prompting pipeline:

  • the type of in-context alignment,
  • where the alignment sits in the prompt (its format),
  • how labels are expressed,
  • how exemplars are retrieved.

A key finding contradicts Tanwar et al. (2023): translating the label set into the target language usually lowers performance. The authors propose query alignment instead, which uses parallel sentences that resemble the query. It works better and can replace or complement X-ICL.

The work gives practical guidance for choosing a strategy based on the resources available for a language, such as an MT system, task data or parallel text.

Key points

  • The study covers 25 low-resource languages from more than 10 language families on three continents, plus 7 higher-resource ones: fra, spa, deu, ita, por, arb and hin.
  • The low-resource data come from MasakhaNews, NusaTranslation and AmericasNLI. The higher-resource languages use TweetSentimentMultilingual, because MARC and CLS are no longer available.
  • How much X-ICL performance drops tracks how much pre-training data exists for the target language.
  • Keeping the high-resource label words unchanged often works best. Making the prompt format more consistent (alignment-after vs. alignment-before vs. tabular-prompting) helps higher-resource languages but not the low-resource ones.
  • Translate-test remains the strongest option when an MT system exists. All experiments ran on a single RTX3090 (24GB) GPU.

Interesting ideas

  • I1. Align the inputs, not the outputs. Instead of translating the label words, show a few source–target sentence pairs that resemble the query. These pairs are selected by monolingual similarity to the query on the target side. This approach could suit any language that has some parallel text but lacks a reliable translation system.
  • I2. Leave labels in the language the model knows best. For weakly represented languages, translated label words can confuse the model rather than help it. This is a useful default to test when building classification prompts for under-resourced languages.
  • I3. Choose the method by available resources. The paper links each resource situation (MT system, task data, parallel corpus) to a preferred technique. This gives teams a simple checklist before running experiments.
  • I4. Check whether results transfer across resource levels. Methods tuned on French or Spanish may fail on smaller languages, as both label alignment and format consistency did here. Reporting results separately by resource level makes such failures visible.
  • I5. Treat prompt layout as a variable to test. Placing alignment text before or after the exemplars, or using a tabular layout, are cheap variants. Testing them separately shows which design choices matter for which languages.

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

🎓Hong Kong University of Science and TechnologyHong Kong · China58 works · 23,058 citations🏛️AI SingaporeSingapore · Singapore2 works · 271 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 1,343 worksLow-resource languages · 166 worksGrammatical error correction & learner language · 80 works

Cite

Cite as Samuel Cahyawijaya, Holy Lovenia and Pascale Fung. 2024. LLMs Are Few-Shot In-Context Low-Resource Language Learners. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.naacl-long.24

@inproceedings{cahyawijaya2024llms,
  title = {{LLMs Are Few-Shot In-Context Low-Resource Language Learners}},
  author = {Samuel Cahyawijaya, Holy Lovenia and Pascale Fung},
  booktitle = {Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  year = {2024},
  doi = {10.18653/v1/2024.naacl-long.24},
  url = {https://doi.org/10.18653/v1/2024.naacl-long.24}
}

References

71 references, 38 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. David Adelani, Jesujoba Alabi, Angela Fan, Julia Kreutzer, Xiaoyu Shen, Machel Reid, Dana Ruiter, Dietrich Klakow, Peter Nabende, Ernie Chang, Tajuddeen Gwadabe, Freshia Sackey, Bonaventure F. P. Dossou, Chris Emezue, Colin Leong, Michael Beukman, Shamsuddeen Muhammad, Guyo Jarso, Oreen Yousuf, Andr…
  2. David Adelani, Graham Neubig, Sebastian Ruder, Shruti Rijhwani, Michael Beukman, Chester Palen-Michel, Constantine Lignos, Jesujoba Alabi, Shamsuddeen Muhammad, Peter Nabende, Cheikh M. Bamba Dione, Andiswa Bukula, Rooweither Mabuya, Bonaventure F. P. Dossou, Blessing Sibanda, Happy Buzaaba, Jonatha…
  3. David Ifeoluwa Adelani, Jade Abbott, Graham Neubig, Daniel D’souza, Julia Kreutzer, Constantine Lignos, Chester Palen-Michel, Happy Buzaaba, Shruti Rijhwani, Sebastian Ruder, Stephen Mayhew, Israel Abebe Azime, Shamsuddeen H. Muhammad, Chris Chinenye Emezue, Joyce Nakatumba-Nabende, Perez Ogayo, Are…
  4. David Ifeoluwa Adelani, Marek Masiak, Israel Abebe Azime, Jesujoba Alabi, Atnafu Lambebo Tonja, Christine Mwase, Odunayo Ogundepo, Bonaventure F. P. Dossou, Akintunde Oladipo, Doreen Nixdorf, Chris Chinenye Emezue, sana al azzawi, Blessing Sibanda, Davis David, Lolwethu Ndolela, Jonathan Mukiibi, Tu…
  5. Muhammad Farid Adilazuarda, Samuel Cahyawijaya, Alham Fikri Aji, Genta Indra Winata, and Ayu Purwarianti. 2024. Lingualchemy: Fusing typological and geographical elements for unseen language generalization. find
  6. Muhammad Farid Adilazuarda, Samuel Cahyawijaya, and Ayu Purwarianti. 2023. The obscure limitation of modular multilingual language models. find
  7. Alham Fikri Aji, Genta Indra Winata, Fajri Koto, Samuel Cahyawijaya, Ade Romadhony, Rahmad Mahendra, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Timothy Baldwin, Jey Han Lau, and Sebastian Ruder. 2022a. One country, 700+ languages: NLP challenges for underrepresented languages and dialects… find
  8. Alham Fikri Aji, Genta Indra Winata, Fajri Koto, Samuel Cahyawijaya, Ade Romadhony, Rahmad Mahendra, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Timothy Baldwin, Jey Han Lau, and Sebastian Ruder. 2022b. One country, 700+ languages: NLP challenges for underrepresented languages and dialects… find
  9. Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, Alessandro Cappelli, Ruxandra Cojocaru, Merouane Debbah, Etienne Goffinet, Daniel Heslow, Julien Launay, Quentin Malartic, Badreddine Noune, Baptiste Pannier, and Guilherme Penedo. 2023. Falcon-40B: an open large language model with state-of-t… find
  10. Akari Asai, Sneha Kudugunta, Xinyan Velocity Yu, Terra Blevins, Hila Gonen, Machel Reid, Yulia Tsvetkov, Sebastian Ruder, and Hannaneh Hajishirzi. 2023. Buffet: Benchmarking large language models for few-shot cross-lingual transfer.
  11. Lucas Bandarkar, Davis Liang, Benjamin Muller, Mikel Artetxe, Satya Narayan Shukla, Donald Husa, Naman Goyal, Abhinandan Krishnan, Luke Zettlemoyer, and Madian Khabsa. 2023. The belebele benchmark: a parallel reading comprehension dataset in 122 language variants. arXiv preprint arXiv:2308.16884.
  12. Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, Quyet V. Do, Yan Xu, and Pascale Fung. 2023. A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity.
  13. Francesco Barbieri, Luis Espinosa Anke, and Jose Camacho-Collados. 2022. XLM-T: Multilingual language models in Twitter for sentiment analysis and beyond. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 258–266, Marseille, France. European Language Resources Asso…
  14. Valerio Basile, Cristina Bosco, Elisabetta Fersini, Debora Nozza, Viviana Patti, Francisco Manuel Rangel Pardo, Paolo Rosso, and Manuela Sanguinetti. 2019. SemEval-2019 task 5: Multilingual detection of hate speech against immigrants and women in Twitter. In Proceedings of the 13th International Wor…
  15. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri…
  16. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020b. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  17. Samuel Cahyawijaya, Holy Lovenia, Alham Fikri Aji, Genta Indra Winata, Bryan Wilie, Rahmad Mahendra, Christian Wibisono, Ade Romadhony, Karissa Vincentio, Fajri Koto, Jennifer Santoso, David Moeljadi, Cahya Wirawan, Frederikus Hudi, Ivan Halim Parmonangan, Ika Alfina, Muhammad Satrio Wicaksono, Ilha… find
  18. Samuel Cahyawijaya, Holy Lovenia, Fajri Koto, Dea Adhista, Emmanuel Dave, Sarah Oktavianti, Salsabil Akbar, Jhonson Lee, Nuur Shadieq, Tjeng Wawan Cenggoro, hanung linuwih, Bryan Wilie, Galih Muridan, Genta Winata, David Moeljadi, Alham Fikri Aji, Ayu Purwarianti, and Pascale Fung. 2023b. Nusawrites… find
  19. Samuel Cahyawijaya, Holy Lovenia, Fajri Koto, Rifki Afina Putri, Emmanuel Dave, Jhonson Lee, Nuur Shadieq, Wawan Cenggoro, Salsabil Maulana Akbar, Muhammad Ihza Mahendra, Dea Annisayanti Putri, Bryan Wilie, Genta Indra Winata, Alham Fikri Aji, Ayu Purwarianti, and Pascale Fung. 2024. Cendol: Open in… find
  20. Samuel Cahyawijaya, Holy Lovenia, Tiezheng Yu, Willy Chung, and Pascale Fung. 2023c. Instructalign: Teaching novel languages with to llms through alignment-based cross-lingual instruction. find
  21. Samuel Cahyawijaya, Genta Indra Winata, Bryan Wilie, Karissa Vincentio, Xiaohong Li, Adhiguna Kuncoro, Sebastian Ruder, Zhi Yuan Lim, Syafri Bahar, Masayu Khodra, Ayu Purwarianti, and Pascale Fung. 2021. IndoNLG: Benchmark and resources for evaluating Indonesian natural language generation. In Proce… find
  22. Vishrav Chaudhary, Yuqing Tang, Francisco Guzmán, Holger Schwenk, and Philipp Koehn. 2019. Low-resource corpus filtering using multilingual sentence embeddings. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 261–266, Florence, Italy. Assoc…
  23. Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet K. Dokania, Philip H. S. Torr, and Marc’Aurelio Ranzato. 2019. On tiny episodic memories in continual learning. find
  24. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emi…
  25. Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel Bowman, Holger Schwenk, and Veselin Stoyanov. 2018. XNLI: Evaluating cross-lingual sentence representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2475–2485, Brussels, Bel… find
  26. Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John Ortega, Ricardo Ramos, Annette Rios, Ivan Vladimir Meza Ruiz, Gustavo Giménez-Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando Coto-Solano, Thang Vu, and Katharina Kann. 2022a. AmericasNLI:…
  27. Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John Ortega, Ricardo Ramos, Annette Rios, Ivan Vladimir Meza Ruiz, Gustavo Giménez-Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando Coto-Solano, Thang Vu, and Katharina Kann. 2022b. AmericasNLI:…
  28. Ahmed El-Kishky, Vishrav Chaudhary, Francisco Guzmán, and Philipp Koehn. 2020. CCAligned: A massive collection of cross-lingual web-document pairs. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5960–5969, Online. Association for Computationa…
  29. Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2022. Language-agnostic BERT sentence embedding. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 878–891, Dublin, Ireland. Association for Computation…
  30. Robert M. French. 1993. Catastrophic interference in connectionist networks: Can it be predicted, can it be prevented? In Proceedings of the 6th International Conference on Neural Information Processing Systems, NIPS’93, page 1176–1177, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc. find
  31. Naman Goyal, Cynthia Gao, Vishrav Chaudhary, Peng-Jen Chen, Guillaume Wenzek, Da Ju, Sanjana Krishnan, Marc’Aurelio Ranzato, Francisco Guzmán, and Angela Fan. 2022. The Flores-101 evaluation benchmark for low-resource and multilingual machine translation. Transactions of the Association for Computat… find
  32. Xisen Jin, Xiang Ren, Daniel Preotiuc-Pietro, and Pengxiang Cheng. 2023. Dataless knowledge fusion by merging weights of language models. In The Eleventh International Conference on Learning Representations. find
  33. Alex Jones, Isaac Caswell, Ishank Saxena, and Orhan Firat. 2023. Bilex rx: Lexical data augmentation for massively multilingual machine translation. find
  34. Anubha Kabra, Emmy Liu, Simran Khanuja, Alham Fikri Aji, Genta Winata, Samuel Cahyawijaya, Anuoluwapo Aremu, Perez Ogayo, and Graham Neubig. 2023. Multi-lingual and multi-cultural figurative language understanding. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8269–82… find
  35. Divyanshu Kakwani, Anoop Kunchukuttan, Satish Golla, Gokul N.C., Avik Bhattacharyya, Mitesh M. Khapra, and Pratyush Kumar. 2020. IndicNLPSuite: Monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. In Findings of the Association for Computation…
  36. Phillip Keung, Yichao Lu, György Szarvas, and Noah A. Smith. 2020. The multilingual Amazon reviews corpus. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4563–4568, Online. Association for Computational Linguistics.
  37. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In ICML 2022 Workshop on Knowledge Retrieval and Language Models.
  38. Fajri Koto, Nurul Aisyah, Haonan Li, and Timothy Baldwin. 2023. Large language models only pass primary school exams in Indonesia: A comprehensive test on IndoMMLU. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12359–12374, Singapore. Association fo… find
  39. Aman Kumar, Himani Shrotriya, Prachi Sahu, Amogh Mishra, Raj Dabre, Ratish Puduppully, Anoop Kunchukuttan, Mitesh M. Khapra, and Pratyush Kumar. 2022. IndicNLG benchmark: Multilingual datasets for diverse NLG tasks in Indic languages. In Proceedings of the 2022 Conference on Empirical Methods in Nat… find
  40. Colin Leong, Joshua Nemecek, Jacob Mansdorfer, Anna Filighera, Abraham Owodunni, and Daniel Whitenack. 2022. Bloom library: Multimodal datasets in 300+ languages for a variety of downstream tasks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8608–8… find
  41. Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Alexander Cosgrove, Christopher D Manning, Christopher Re, Diana Acosta-Navas, Drew Arad Hu… find
  42. 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, Veselin Stoyano…
  43. 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, Veselin Stoyano…
  44. Holy Lovenia, Wenliang Dai, Samuel Cahyawijaya, Ziwei Ji, and Pascale Fung. 2023. Negative object presence evaluation (nope) to measure object hallucination in vision-language models. arXiv preprint arXiv:2310.05338. find
  45. Holy Lovenia, Rahmad Mahendra, Salsabil Maulana Akbar, Lester James V. Miranda, Jennifer Santoso, Elyanah Aco, Akhdan Fadhilah, Jonibek Mansurov, Joseph Marvin Imperial, Onno P. Kampman, Joel Ruben Antony Moniz, Muhammad Ravi Shulthan Habibi, Frederikus Hudi, Railey Montalan, Ryan Ignatius, Joanito… find
  46. Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2022. Rethinking the role of demonstrations: What makes in-context learning work? In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11048–11064, Ab…
  47. Peter Prettenhofer and Benno Stein. 2010. Cross-language text classification using structural correspondence learning. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 1118–1127, Uppsala, Sweden. Association for Computational Linguistics.
  48. Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen… find
  49. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
  50. Nils Reimers and Iryna Gurevych. 2020. Making monolingual sentence embeddings multilingual using knowledge distillation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4512–4525, Online. Association for Computational Linguistics.
  51. David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy Lillicrap, and Gregory Wayne. 2019. Experience replay for continual learning. In Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc. find
  52. Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, et al. 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100. find
  53. Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong, and Francisco Guzmán. 2021. 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… find
  54. Freda Shi, Mirac Suzgun, Markus Freitag, Xuezhi Wang, Suraj Srivats, Soroush Vosoughi, Hyung Won Chung, Yi Tay, Sebastian Ruder, Denny Zhou, Dipanjan Das, and Jason Wei. 2023. Language models are multilingual chain-of-thought reasoners. In The Eleventh International Conference on Learning Representa…
  55. Shaden Smith, Mostofa Patwary, Brandon Norick, Patrick LeGresley, Samyam Rajbhandari, Jared Casper, Zhun Liu, Shrimai Prabhumoye, George Zerveas, Vijay Korthikanti, Elton Zhang, Rewon Child, Reza Yazdani Aminabadi, Julie Bernauer, Xia Song, Mohammad Shoeybi, Yuxiong He, Michael Houston, Saurabh Tiwa…
  56. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R. Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W. Kocurek, Ali Safaya, Ali Tazarv, Al…
  57. Eshaan Tanwar, Subhabrata Dutta, Manish Borthakur, and Tanmoy Chakraborty. 2023. Multilingual LLMs are better cross-lingual in-context learners with alignment. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6292–6307, Toronto…
  58. MosaicML NLP Team. 2023. Introducing mpt-7b: A new standard for open-source, commercially usable llms. Accessed: 2023-05-05. find
  59. NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hof… find
  60. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou. 2022. Chain of thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems.
  61. Haryo Akbarianto Wibowo, Erland Hilman Fuadi, Made Nindyatama Nityasya, Radityo Eko Prasojo, and Alham Fikri Aji. 2023. Copal-id: Indonesian language reasoning with local culture and nuances. find
  62. Bryan Wilie, Karissa Vincentio, Genta Indra Winata, Samuel Cahyawijaya, Xiaohong Li, Zhi Yuan Lim, Sidik Soleman, Rahmad Mahendra, Pascale Fung, Syafri Bahar, and Ayu Purwarianti. 2020. IndoNLU: Benchmark and resources for evaluating Indonesian natural language understanding. In Proceedings of the 1…
  63. Genta Winata, Shijie Wu, Mayank Kulkarni, Thamar Solorio, and Daniel Preotiuc-Pietro. 2022a. Cross-lingual few-shot learning on unseen languages. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Confere… find
  64. Genta Indra Winata, Alham Fikri Aji, Samuel Cahyawijaya, Rahmad Mahendra, Fajri Koto, Ade Romadhony, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Pascale Fung, et al. 2022b. Nusax: Multilingual parallel sentiment dataset for 10 indonesian local languages. arXiv preprint arXiv:2205.15960.
  65. Genta Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, and Pascale Fung. 2021a. Are multilingual models effective in code-switching? In Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching, pages 142–153, Online. Association for Comput… find
  66. Genta Indra Winata, Andrea Madotto, Zhaojiang Lin, Rosanne Liu, Jason Yosinski, and Pascale Fung. 2021b. Language models are few-shot multilingual learners. In Proceedings of the 1st Workshop on Multilingual Representation Learning, pages 1–15.
  67. Genta Indra Winata, Andrea Madotto, Zhaojiang Lin, Rosanne Liu, Jason Yosinski, and Pascale Fung. 2021c. Language models are few-shot multilingual learners. In Proceedings of the 1st Workshop on Multilingual Representation Learning, pages 1–15, Punta Cana, Dominican Republic. Association for Computa…
  68. Sang Michael Xie, Aditi Raghunathan, Percy Liang, and Tengyu Ma. 2022. An explanation of in-context learning as implicit bayesian inference. In International Conference on Learning Representations.
  69. Zheng-Xin Yong, Hailey Schoelkopf, Niklas Muennighoff, Alham Fikri Aji, David Ifeoluwa Adelani, Khalid Almubarak, M Saiful Bari, Lintang Sutawika, Jungo Kasai, Ahmed Baruwa, Genta Indra Winata, Stella Biderman, Dragomir Radev, and Vassilina Nikoulina. 2022. Bloom+1: Adding language support to bloom…
  70. Zheng-Xin Yong, Ruochen Zhang, Jessica Zosa Forde, Skyler Wang, Samuel Cahyawijaya, Holy Lovenia, Genta Indra Winata, Lintang Sutawika, Jan Christian Blaise Cruz, Long Phan, et al. 2023. Prompting multilingual large language models to generate code-mixed texts: The case of south east asian languages… find
  71. Ruochen Zhang, Samuel Cahyawijaya, Jan Christian Blaise Cruz, and Alham Fikri Aji. 2023. Multilingual large language models are not (yet) code-switchers.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/cahyawijaya-2024-llms-are-few-shot-context/