mlsanityData to 14 Oct 2026

Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities

arXiv 2510.07037 ↗First posted 8 Oct 2025cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Amidst the rapid advances of large language models (LLMs), most LLMs still struggle with mixed-language inputs, limited Codeswitching (CSW) datasets, and evaluation biases, which hinder their deployment in multilingual societies. This survey provides the first comprehensive analysis of CSW-aware LLM research, reviewing 327 studies spanning five research areas, 15+ NLP tasks, 30+ datasets, and 80+ languages. We categorize recent advances by architecture, training strategy, and evaluation methodology, outlining how LLMs have reshaped CSW modeling and identifying the challenges that persist. The paper concludes with a roadmap that emphasizes the need for inclusive datasets, fair evaluation, and linguistically grounded models to achieve truly multilingual capabilities https://github.com/lingo-iitgn/awesome-code-mixing/.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 139 of its 332 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

139 of 332 references.

References · 139

  1. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  2. 2018Neural Network Acceptability Judgmentscited by 958
  3. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  4. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
  5. 2017Word Translation Without Parallel Datacited by 487
  6. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 340
  7. 2020MLSUM: The Multilingual Summarization Corpuscited by 121
  8. 2023The Semantic Scholar Open Data Platformcited by 118
  9. 2020GLUECoS : An Evaluation Benchmark for Code-Switched NLPcited by 102
  10. 2020LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluationcited by 93
  11. 2023Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?cited by 88
  12. 2023GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformercited by 88
38 more
  1. 2020CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLPcited by 79
  2. 2019A Survey of Code-switched Speech and Language Processingcited by 75
  3. 2024Understanding and Mitigating Language Confusion in LLMscited by 75
  4. 2022NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languagescited by 68
  5. 2023Multilingual Large Language Models Are Not (Yet) Code-Switcherscited by 65
  6. 2020SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweetscited by 62
  7. 2023A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologiescited by 59
  8. 2023MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Taskscited by 57
  9. 2021Are Multilingual Models Effective in Code-Switching?cited by 56
  10. 2019Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentencescited by 55
  11. 2021Multilingual and code-switching ASR challenges for low resource Indian languagescited by 53
  12. 2023Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languagescited by 51
  13. 2021MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERcited by 42
  14. 2023PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuningcited by 39
  15. 2024Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languagescited by 36
  16. 2022L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Modelscited by 34
  17. 2024Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understandingcited by 34
  18. 2019Overview for the Second Shared Task on Language Identification in Code-Switched Datacited by 33
  19. 2016Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Textcited by 31
  20. 2020A New Dataset for Natural Language Inference from Code-mixed Conversationscited by 29
  21. 2021From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Textcited by 29
  22. 2024Code-Switching Curriculum Learning for Multilingual Transfer in LLMscited by 27
  23. 2022End-to-End Speech Translation for Code Switched Speechcited by 26
  24. 2021Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Fillingcited by 25
  25. 2023Enhancing Code-switching Speech Recognition with Interactive Language Biasescited by 21
  26. 2019From English to Code-Switching: Transfer Learning with Strong Morphological Cluescited by 18
  27. 2021DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Textcited by 18
  28. 2021Challenges and Limitations with the Metrics Measuring the Complexity of Code-Mixed Textcited by 18
  29. 2021Arabic Code-Switching Speech Recognition using Monolingual Datacited by 17
  30. 2022TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baselinecited by 17
  31. 2021Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixingcited by 16
  32. 2023Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparationcited by 16
  33. 2025Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Trainingcited by 16
  34. 2018Code-Switching Language Modeling using Syntax-Aware Multi-Task Learningcited by 15
  35. 2025SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Datasetcited by 14
  36. 2019A Deep Generative Model for Code-Switched Textcited by 13
  37. 2021Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillationcited by 13
  38. 2023X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agentscited by 13

50 most cited of 139 All 139 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengalicited by 1
  2. 2026Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text in Multilingual Encoderscited by 0
  3. 2026Safety Alignment Illusion: The Cross-Lingual Safety Gap in LLMscited by 0
  4. 2026IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixingcited by 0
  5. 2026CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writingcited by 0