Papers
Topics
Authors
Recent
Search
2000 character limit reached

Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching

Published 24 Oct 2024 in cs.CL | (2410.18436v2)

Abstract: Recent LLMs demonstrate multilingual abilities, yet they are English-centric due to dominance of English in training corpora. The limited resource for low-resource languages remains a crucial challenge. Code-switching (CS), a phenomenon where multilingual speakers alternate between languages in a discourse, can convey subtle cultural and linguistic nuances that can be otherwise lost in translation and elicits language-specific knowledge in human communications. In light of this, we investigate whether code-switching can 'activate', or identify and leverage knowledge for reasoning when LLMs solve low-resource language tasks. To facilitate the research, we first present EnKoQA, a synthetic English-Korean CS question-answering dataset. We provide comprehensive analysis on a variety of multilingual LLMs by subdividing activation process into knowledge identification and knowledge leveraging. Our results demonstrate that compared to English text, CS can faithfully activate knowledge inside LLMs especially on language-specific domains, suggesting the potential of code-switching on low-resource language tasks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (25)
  1. LinCE: A centralized benchmark for linguistic code-switching evaluation. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 1803–1813, Marseille, France. European Language Resources Association.
  2. Anthropic. 2024. Claude 3.5 sonnet.
  3. A survey of code-switching: Linguistic and social perspectives for language technologies. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1654–1666, Online. Association for Computational Linguistics.
  4. The llama 3 herd of models. Preprint, arXiv:2407.21783.
  5. Gemma Team. 2024. Gemma 2: Improving open language models at a practical size.
  6. Roberto Heredia and Jeanette Altarriba. 2001. Bilingual language mixing: Why do bilinguals code-switch? Current Directions in Psychological Science - CURR DIRECTIONS PSYCHOL SCI, 10:164–168.
  7. Evaluating code-switching translation with large language models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6381–6394, Torino, Italia. ELRA and ICCL.
  8. GLUECoS: An evaluation benchmark for code-switched NLP. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3575–3585, Online. Association for Computational Linguistics.
  9. Solar 10.7b: Scaling large language models with simple yet effective depth up-scaling. Preprint, arXiv:2312.15166.
  10. CLIcK: A benchmark dataset of cultural and linguistic intelligence in Korean. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3335–3346, Torino, Italia. ELRA and ICCL.
  11. Synthetic data generation with large language models for text classification: Potential and limitations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10443–10461, Singapore. Association for Computational Linguistics.
  12. C. Myers-Scotton. 1997. Duelling Languages: Grammatical Structure in Codeswitching. Clarendon Press.
  13. OpenAI. 2023. Gpt-4 technical report. Preprint, arXiv:2303.08774.
  14. Eunsun Park and Hongoak Yun. 2021. The grammatical constraint and grammatical encoding of Korean-English code switching. The Journal of Mirae English Language and Literature, 26(1):177–204.
  15. Shana Poplack. 1980. Sometimes i’ll start a sentence in spanish y termino en espaÑol: toward a typology of code-switching 1. Linguistics, 18:581–618.
  16. Language modeling for code-mixing: The role of linguistic theory based synthetic data. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1543–1553, Melbourne, Australia. Association for Computational Linguistics.
  17. GCM: A toolkit for generating synthetic code-mixed text. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 205–211, Online. Association for Computational Linguistics.
  18. Offensive content detection via synthetic code-switched text. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6617–6624, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  19. In-context mixing (ICM): Code-mixed prompts for multilingual LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4162–4176, Bangkok, Thailand. Association for Computational Linguistics.
  20. HAE-RAE bench: Evaluation of Korean knowledge in language models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7993–8007, Torino, Italia. ELRA and ICCL.
  21. Chain-of-thought prompting elicits reasoning in large language models. Preprint, arXiv:2201.11903.
  22. Prompting multilingual large language models to generate code-mixed texts: The case of south East Asian languages. In Proceedings of the 6th Workshop on Computational Approaches to Linguistic Code-Switching, pages 43–63, Singapore. Association for Computational Linguistics.
  23. Multilingual large language models are not (yet) code-switchers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12567–12582, Singapore. Association for Computational Linguistics.
  24. Siren’s song in the ai ocean: a survey on hallucination in large language models. arXiv preprint arXiv:2309.01219.
  25. Judging llm-as-a-judge with mt-bench and chatbot arena. Preprint, arXiv:2306.05685.
Citations (1)

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.