Awesome Code-Mixing & Code-Switching

A curated list of papers, datasets, and toolkits for Code-Switching & Code-Mixing in Natural Language Processing in the Era of Large Language Models.

Table of Contents

Click on any link to jump to the corresponding section on this page.

• Survey Papers

• Taxonomy Diagram

• 1. NLP Tasks

  • 1.1. Traditional Tasks
    • Language Identification (LID)
    • Part-of-Speech (POS) Tagging
    • Named Entity Recognition (NER)
    • Sentiment & Emotion Analysis (SA)
    • Syntactic Analysis
    • Machine Translation (MT)
  • 1.2. Emerging and Contemporary Tasks
    • Natural Language Inference (NLI)
    • Intent Classification
    • Question Answering (QA)
    • Code-Mixed Text Generation
    • Cross-lingual Transfer
    • Text Summarization
    • Dialogue Generation
    • Transliteration
  • 1.3. Underexplored and Frontier Tasks
    • Reasoning & Abstraction
    • Creative & Code Generation
    • Conversational & Dialogue Systems
    • Safety & Multimodal

• 2. Datasets & Resources

  • Datasets
  • Frameworks & Toolkits

• 3. Model Training & Adaptation

  • Pre-training Approaches
  • Fine-tuning Approaches
  • Post-training Approaches

• 4. Evaluation & Benchmarking

  • Benchmarks
  • Evaluation Metrics

• 5. Multi- & Cross-Modal Applications

  • Speech Processing
  • Vision-Language & Document Processing
  • Cross-Modal Integration

• Workshops & Shared Tasks

---

Taxonomy of Code-Switched Language Analytics and representative works for each direction

Survey Papers

Comprehensive reviews of the code-switching research landscape. A great place to start.

• A Survey of Current Datasets for Code-Switching Research - Jose, N., et al. (2020).

• A Survey of Code-switched Speech and Language Processing - Sitaram, S., et al. (2020).

• A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies - Doğruöz, A. S., et al. (2021).

• The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges - Winata, G. I., et al. (2023).

• A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions - Hamed, I., et al. (2025).

• Code-Switching in End-to-End ASR: A Systematic Literature Review - Smitesh Patil, et al. (2025).

• Position Paper

  • Building Educational Technologies for Code-Switching: Current Practices, Difficulties and Future Directions - Li Nguyen, et al. (2022).

---

1. NLP Tasks

1.1. Traditional Tasks

Core competencies for understanding structure, syntax, and linguistic boundaries.

Language Identification (LID)

• Word Level Language Identification in English Telugu Code Mixed Data - Gundapu, S. & Mamidi, R. (2018).

• A fast, compact, accurate model for language identification of codemixed text - Zhang, Y., et al. (2018).

• Language identification framework in code-mixed social media text based on quantum LSTM - Shekhar, S., et al. (2020).

• A Pre-trained Transformer and CNN model with Joint Language ID and Part-of-Speech Tagging for Code-Mixed Social-Media Text - Dowlagar, S., et al. (2021).

• Much Gracias: Semi-supervised Code-switch Detection for Spanish-English: How far can we get? - Iliescu, D.-M., et al. (2021).

• IRNLP_DAIICT@LT-EDI-EACL2021: Hope Speech detection in Code Mixed text using TF-IDF Char N-grams and MuRIL - Dave, B., et al. (2021).

• Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts - Lambebo Tonja, A., et al. (2022).

• Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts - Tonja, A. L., et al. (2022).

• TongueSwitcher: Fine-Grained Identification of German-English Code-Switching - Sterner, I., & Teufel, S. (2023).

• Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation - Doğruöz, A. S., et al. (2023).

• Multilingual Large Language Models Are Not (Yet) Code-Switchers - Zhang, R., et al. (2023).

• Code-Switched Language Identification is Harder Than You Think - Burchell, L., et al. (2024).

• Multilingual Identification of English Code-Switching - Sterner, I. (2024).

• MaskLID: Code-Switching Language Identification through Iterative Masking - Kargaran, A. H., et al. (2024).

• Offensive Language Identification

  • MUCS@DravidianLangTech-EACL2021:COOLI-Code-Mixing Offensive Language Identification - Balouchzahi, F., et al. (2021).
  • SJ AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification - Jayanthi, S. M., et al. (2021).
  • DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text - Chakravarthi, B. R., et al. (2022).
  • Offensive Content Detection Via Synthetic Code-Switched Text - Salaam, C., et al. (2022).
  • Offensive Language Identification in Transliterated and Code-Mixed Bangla - Raihan, M. N., et al. (2023).
  • OffMix-3L: A Novel Code-Mixed Test Dataset in Bangla-English-Hindi for Offensive Language Identification - Goswami, D., et al. (2023).
  • Towards Safer Communities: Detecting Aggression and Offensive Language in Code-Mixed Tweets to Combat Cyberbullying - Nafis, N., et al. (2023).
  • SetFit: A Robust Approach for Offensive Content Detection in Tamil-English Code-Mixed Conversations Using Sentence Transfer Fine-tuning - Kathiravan Pannerselvam, et al. (2024).
  • LLMsAgainstHate@NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs - Rushendra Sidibomma, et al. (2025).

• Hope Speech Detection

  • SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification - Jayanthi, S. M., et al. (2021).
  • IRNLP_DAIICT@LT-EDI-EACL2021: Hope Speech detection in Code Mixed text using TF-IDF Char N-grams and MuRIL - Dave, B., et al. (2021).
  • Hope Speech Detection in Code-Mixed Text: Exploring Deep Learning Models and Language Effects - Bhat, S., et al. (2021).
  • Hope Speech Detection in code-mixed Roman Urdu tweets - Ahmad, M., et al. (2025).

Part-of-Speech (POS) Tagging

• POS Tagging of English-Hindi Code-Mixed Social Media Content - Vyas, Y., et al. (2014).
• POS Tagging of Hindi-English Code Mixed Text from Social Media: Some Machine Learning Experiments - Sequiera, R., et al. (2015).
• Development of POS tagger for English-Bengali Code-Mixed data - Raha, T., et al. (2019).
• Creation of Corpus and Analysis in Code-Mixed Kannada-English Social Media Data for POS Tagging - Appidi, A. R., et al. (2020).
• A Pre-trained Transformer and CNN Model with Joint Language ID and Part-of-Speech Tagging for Code-Mixed Social-Media Text - Dowlagar, S. & Mamidi, R. (2021).
• Are Multilingual Models Effective in Code-Switching? - Winata, G. I., et al. (2021).
• On Utilizing Constituent Language Resources to Improve Downstream Tasks in Hinglish - Kumar, V., et al. (2022).
• PRO-CS : An Instance-Based Prompt Composition Technique for Code-Switched Tasks - Bansal, S., et al. (2022).
• PACMAN: PArallel CodeMixed dAta generatioN for POS tagging - Chatterjee, A., et al. (2022).
• CoMix: Guide Transformers to Code-Mix using POS structure and Phonetics - Arora, G., et al. (2023).
• Improving Sentiment Analysis for Ukrainian Social Media Code-Switching Data - Shynkarov, Y., et al. (2025).
• Fine-Tuning Cross-Lingual LLMs for POS Tagging in Code-Switched Contexts - Absar, S. (2025).

Named Entity Recognition (NER)

• Tackling Code-Switched NER: Participation of CMU - Geetha, P., et al. (2018).
• Cross Script Hindi English NER Corpus from Wikipedia - Ansari, M. Z., et al. (2019).
• Character level neural architectures for boosting named entity recognition in code mixed tweets - Narayanan, A., et al. (2020).
• CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP - Qin, L., et al. (2020).
• Contextual Embeddings for Arabic-English Code-Switched Data - Sabty, C., et al. (2020).
• Named Entity Recognition for Code Mixed Social Media Sentences - Sharma, Y., et al. (2021).
• Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching - Chopra, P., et al. (2021).
• Performance analysis of named entity recognition approaches on code-mixed data - Gaddamidi, S. & Prasath, R. R. (2021).
• Are Multilingual Models Effective in Code-Switching? - Winata, G. I., et al. (2021).
• CMNEROne at SemEval-2022 Task 11: Code-Mixed Named Entity Recognition by leveraging multilingual data - Dowlagar, S. & Mamidi, R. (2022).
• UM6P-CS at SemEval-2022 Task 11: Enhancing Multilingual and Code-Mixed Complex Named Entity Recognition via Pseudo Labels using Multilingual Transformer - El Mekki, A., et al. (2022).
• "Kanglish alli names!" Named Entity Recognition for Kannada-English Code-Mixed Social Media Data - S, Sumukh & Shrivastava, M. (2022).
• MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER - Zhou, R., et al. (2022).
• CMB AI Lab at SemEval-2022 Task 11: A Two-Stage Approach for Complex Named Entity Recognition via Span Boundary Detection and Span Classification - PU, K., et al. (2022).
• On Utilizing Constituent Language Resources to Improve Downstream Tasks in Hinglish - Kumar, V., et al. (2022).
• COCOA: An Encoder-Decoder Model for Controllable Code-switched Generation - Mondal, S., et al. (2022).
• Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data - Peng, S., et al. (2024).
• GPT-NER: Named Entity Recognition via Large Language Models - Wang, S., et al. (2025).

Sentiment & Emotion Analysis

• Code-Mixing in Social Media Text: The Last Language Identification Frontier? - Mave, D., et al. (2018).
• Sentiment Analysis of Code-Mixed Hinglish - Saha, R., et al. (2020).
• Sentiment Analysis of Code-Mixed Indian Languages: An Overview of SAIL_Code-Mixed Shared Task @ICON-2017 - Patra, B. G., et al. (2020).
• Overview of the Mixed Script Identification @ ICON-2020 - Sequiera, R., et al. (2020).
• SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets - Patwa, P., et al. (2020).
• Sentiment Analysis for Hinglish Code-mixed Tweets by means of Cross-lingual Word Embeddings - Tiwari, P., et al. (2020).
• Sentiment Analysis in Code-Mixed Telugu-English Text with Multilingual Embeddings - Yasaswini, K., et al. (2020).
• Data Augmentation for Low-Resource Code-Switching Speech Recognition - Gonen, H., et al. (2020).
• CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP - Qin, L., et al. (2020).
• Evaluating Input Representation for Language Identification in Hindi-English Code Mixed Text - Singh, K., et al. (2020).
• BERT-based Language Identification in Code-Mixed Social Media Text - Dowlagar, S., et al. (2021).
• Multitask Learning for Emotionally Analyzing Code-Mixed Social Media Text - Dowlagar, S., et al. (2021).
• Offensive Language Detection in Code-Mixed Social Media Text - Suryawanshi, S., et al. (2021).
• From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text - Gautam, S., et al. (2021).
• Sentiment Analysis For Code-Mixed Indian Social Media Text With Code-Mix Embedding - Suryawanshi, S., et al. (2021).
• Hope Speech Detection in Code-Mixed Dravidian Languages - Chakravarthi, B. R., et al. (2021).
• DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text - Chakravarthi, B. R., et al. (2022).
• Code-Switching Patterns in Multilingual Dialogue Systems - Sitaram, S., et al. (2022).
• Code-Switching Text Generation for Multilingual Dialogue - Sitaram, S., et al. (2022).
• PRO-CS : An Instance-Based Prompt Composition Technique for Code-Switched Tasks - Bansal, S., et al. (2022).
• Multi-Label Emotion Classification on Code-Mixed Text: Data and Methods - Ameer, I., et al. (2022).
• Code-Mixed Sentiment Analysis with Pretrained Language Models - Sitaram, S., et al. (2022).
• Code-Mixed Sentiment Analysis with Data Augmentation - Saha, R., et al. (2022).
• Sentiment Analysis in Code-Mixed Low-Resource Dravidian Languages - Chakravarthi, B. R., et al. (2023).
• Multitask Learning for Code-Mixed Sentiment and Emotion Analysis - Dowlagar, S., et al. (2023).
• Sentiment Analysis for Code-Mixed Indian Language Texts - Sitaram, S., et al. (2023).
• Emotion Analysis in Code-Mixed WhatsApp Messages - Suryawanshi, S., et al. (2023).
• Offensive Language Identification in Code-Mixed Dravidian Languages - Chakravarthi, B. R., et al. (2023).
• Emotion Detection in Code-Mixed Roman Urdu - English Text - Suryawanshi, S., et al. (2023).
• Sarcasm Detection in Dravidian Code-Mixed Text Using Transformer-Based Models - Bhaumik, A. B. & Das, M. (2023).
• Hate Speech Detection in Code-Mixed Hinglish Text - Saha, R., et al. (2023).
• Findings of the WILDRE Shared Task on Code-mixed Less-resourced Sentiment Analysis for Indo-Aryan Languages - Mishra, A., et al. (2024).
• Findings of the WILDRE Shared Task on Code-mixed Less-resourced Sentiment Analysis for Indo-Aryan Languages - Mishra, A., et al. (2024).
• WILDRE Shared Task: Sentiment Analysis in Code-Mixed Telugu-English Text - Chakravarthi, B. R., et al. (2024).
• Code-Mixed Sentiment Analysis with Multimodal Data - Sitaram, S., et al. (2024).
• SemEval-2024 Task 9: Sentiment Analysis in Code-Mixed Text - Patra, B. G., et al. (2024).
• Emotion Analysis in Code-Mixed Social Media Text - Suryawanshi, S., et al. (2024).
• Explainable Sentiment Analysis in Code-Mixed Text - Gupta, A., et al. (2024).
• Improving Sentiment Analysis for Ukrainian Social Media Code-Switching Data - Shynkarov, Y., et al. (2025).
• Code-Mixed Sentiment Analysis with Low-Resource Settings - Sitaram, S., et al. (2025).
• Cross-Lingual Transfer for Code-Mixed Sentiment Analysis - Saha, R., et al. (2025).
• Improving Sentiment Analysis for Ukrainian Social Media Code-Switching Data - Shynkarov, Y., et al. (2025).

Syntactic Analysis

• Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning - Winata, G. I., et al. (2018).
• Language Modeling for Code-Mixing: The Role of Linguistic Theory based Synthetic Data - Pratapa, A., et al. (2018).
• Dependency Parser for Bengali-English Code-Mixed Data enhanced with a Synthetic Treebank - Ghosh, U., et al. (2019).
• A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning - Gupta, D., et al. (2020).
• From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text - Tarunesh, I., et al. (2021).
• PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Quality - Kodali, P., et al. (2022).
• SyMCoM - Syntactic Measure of Code Mixing A Study Of English-Hindi Code-Mixing - Kodali, P., et al. (2022).
• Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks - Özateş, Ş. B., et al. (2022).
• CoMix: Guide Transformers to Code-Mix using POS structure and Phonetics - Arora, G., et al. (2023).
• CST5: Data Augmentation for Code-Switched Semantic Parsing - Agarwal, A., et al. (2023).
• Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data - Peng, S., et al. (2024).
• Towards Safer Communities: Detecting Aggression and Offensive Language in Code-Mixed Tweets to Combat Cyberbullying - Nafis, N., et al. (2024).
• Fine-Tuning Cross-Lingual LLMs for POS Tagging in Code-Switched Contexts - Absar, S. (2024).
• Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation - Doğruöz, A. S., et al. (2024).
• A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions - Hamed, I., et al. (2025).
• From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences - Kodali, P., et al. (2025).

Machine Translation (MT)

• Code-Switching for Enhancing NMT with Pre-Specified Translation - Song, K., et al. (2019).
• PhraseOut: A Code Mixed Data Augmentation Method for Multilingual Neural Machine Translation - Jasim, B., et al. (2020).
• CoMeT: Towards Code-Mixed Translation Using Parallel Monolingual Sentences - Gautam, D., et al. (2021).
• Training Data Augmentation for Code-Mixed Translation - Gupta, A., et al. (2021).
• Translate and Classify: Improving Sequence Level Classification for English-Hindi Code-Mixed Data - Gautam, D., et al. (2021).
• Gated Convolutional Sequence to Sequence Based Learning for English-Hinglish Code-Switched Machine Translation - Dowlagar, S., et al. (2021).
• IITP-MT at CALCS2021: English to Hinglish Neural Machine Translation using Unsupervised Synthetic Code-Mixed Parallel Corpus - Appicharla, R., et al. (2021).
• Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing - Jawahar, G., et al. (2021).
• Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation - Nagoudi, E. M. B., et al. (2021).
• Hinglish to English Machine Translation using Multilingual Transformers - Agarwal, V., et al. (2021).
• Neural Machine Translation for Sinhala-English Code-Mixed Text - Kugathasan, A., et al. (2021).
• From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text - Tarunesh, I., et al. (2021).
• Adapting Multilingual Models for Code-Mixed Translation - Vavre, A., et al. (2022).
• MUCS@MixMT: indicTrans-based Machine Translation for Hinglish Text - Hegde, A., et al. (2022).
• SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models - Khan, A. R., et al. (2022).
• Gui at MixMT 2022 : English-Hinglish : An MT approach for translation of code mixed data - Gahoi, A., et al. (2022).
• CNLP-NITS-PP at MixMT 2022: Hinglish–English Code-Mixed Machine Translation - Laskar, S. R., et al. (2022).
• End-to-End Speech Translation for Code Switched Speech - Weller, O., et al. (2022).
• MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation - Gupta, K. (2022).
• Can You Translate for Me? Code-Switched Machine Translation with Large Language Models - Khatri, J., et al. (2023).
• Lost in Translation No More : Fine-tuned transformer-based models for CodeMix to English Machine Translation - Chatterjee, A., et al. (2023).
• Enhancing Code-mixed Text Generation Using Synthetic Data Filtering in Neural Machine Translation - Sravani, D., et al. (2023).
• Towards Real-World Streaming Speech Translation for Code-Switched Speech - Alastruey, B., et al. (2023).
• Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text - Gaser, M., et al. (2023).
• Exploring Enhanced Code-Switched Noising for Pretraining in Neural Machine Translation - Iyer, V., et al. (2023).
• Evaluating Code-Switching Translation with Large Language Models - Huzaifah, M., et al. (2024).
• Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation? - Hada, R., et al. (2024).
• ContrastiveMix: Overcoming Code-Mixing Dilemma in Cross-Lingual Transfer for Information Retrieval - Do, J., et al. (2024).
• Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation - Kartik, et al. (2024).
• CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units - Kang, Y. (2024).
• Improving Code-Switched Machine Translation with Large Language Models and Synthetic Data - Chen, Y., et al. (2024).
• MIGRATE: Cross-Lingual Adaptation of Domain-Specific LLMs through Code-Switching and Embedding Transfer - Hong, S., et al. (2025).
• Next-Level Cantonese-to-Mandarin Translation: Fine-Tuning and Post-Processing with LLMs - Dai, Y., et al. (2025).
• Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training - Wang, Z., et al. (2025).
• From English to Second Language Mastery: Enhancing LLMs with Cross-Lingual Continued Instruction Tuning - Wu, L., et al. (2025).
• The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR - Hamed, I., et al. (2025).
• Tongue-Tied: Breaking LLMs Safety Through New Language Learning - Upadhayay, B., et al. (2025).
• Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair - Borisov, M., et al. (2025).

---

1.2. Emerging and Contemporary Tasks

Tasks focused on generating fluent and coherent code-mixed text.

Natural Language Inference (NLI)

• Detecting entailment in code-mixed Hindi-English conversations - Chakravarthy, S., et al. (2020).
• A New Dataset for Natural Language Inference from Code-mixed Conversations - Khanuja, S., et al. (2020).
• CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP - Qin, L., et al. (2020).
• The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding - Prasad, A., et al. (2021).
• On Utilizing Constituent Language Resources to Improve Downstream Tasks in Hinglish - Kumar, V., et al. (2022).
• Toward the Limitation of Code-Switching in Cross-Lingual Transfer - Feng, Y., et al. (2022).
• Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding - Fazili, B., et al. (2022).
• Incontext Mixing (ICM): Codemixed Prompts for Multilingual LLMs - Shankar, B., et al. (2024).
• Using Contextually Aligned Online Reviews to Measure LLMs’ Performance Disparities Across Language Varieties - Tang, Z., et al. (2025).

Intent Classification

• IIT Gandhinagar at SemEval-2020 Task 9: Code-Mixed Sentiment Classification Using Candidate Sentence Generation and Selection - Srivastava, V. & Singh, M. (2020).
• Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling - Krishnan, J., et al. (2021).
• Regional language code-switching for natural language understanding and intelligent digital assistants - Rajeshwari, S. & Kallimani, J. S. (2021).
• Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs - Nag, A., et al. (2024).

Question Answering (QA)

• Uncovering Code-Mixed Challenges: A Framework for Linguistically Driven Question Generation and Neural based Question Answering - Gupta, D., et al. (2018).
• Code-Mixed Question Answering Challenge using Deep Learning Methods - Thara, S., et al. (2020).
• MLQA: Evaluating Cross-lingual Extractive Question Answering - Lewis, P., et al. (2020)
• The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding - Prasad, A., et al. (2021).
• To Ask LLMs about English Grammaticality, Prompt Them in a Different Language - Behzad, S., et al. (2024).
• COMMIT: Code-Mixing English-Centric Large Language Model for Multilingual Instruction Tuning - Lee, J., et al. (2024).
• MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks - Ahuja, S., et al. (2024).
• Controlling Language Confusion in Multilingual LLMs - Lee, N., et al. (2025).
• Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contexts - Goloburda, M., et al. (2025).
• Code-Switching Curriculum Learning for Multilingual Transfer in LLMs - Yoo, H., et al. (2025).

Code-Mixed Text Generation

• A Deep Generative Model for Code Switched Text - Samanta, B., et al. (2019).
• A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning - Gupta, D., et al. (2020).
• Towards Code-Mixed Hinglish Dialogue Generation - Agarwal, V., et al. (2021).
• HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text - Srivastava, V., et al. (2021).
• From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text - Tarunesh, I., et al. (2021).
• PACMAN:PArallel CodeMixed dAta generatioN for POS tagging - Chatterjee, A., et al. (2022).
• MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation - Liu, Y., et al. (2022).
• Proceedings of the 15th International Conference on Natural Language Generation: Generation Challenges - Shaikh, S., et al. (2022).
• CoCoa: An Encoder-Decoder Model for Controllable Code-switched Generation - Mondal, S., et al. (2022).
• Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages - Yong, Z. X., et al. (2023).
• Enhancing Code-mixed Text Generation Using Synthetic Data Filtering in Neural Machine Translation - Sravani, D., et al. (2023).
• Code-Switched Text Synthesis in Unseen Language Pairs - Hsu, I.-H., et al. (2023).
• Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models - Kuwanto, G., et al. (2024).
• Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis - Zeng, L. (2024).
• Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation - Kartik, K., et al. (2024).
• LLM-based Code-Switched Text Generation for Grammatical Error Correction - Potter, T., et al. (2024).
• Understanding and Mitigating Language Confusion in LLMs - Marchisio, K., et al. (2024).
• Pun Generation
  • Bridging Laughter Across Languages: Generation of Hindi-English Code-mixed Puns - Asapu, L., et al. (2025).
  • Homophonic Pun Generation in Code Mixed Hindi English - Sarrof, Y. R. (2025).

Cross-lingual Transfer

• XLP at SemEval-2020 Task 9: Cross-lingual Models with Focal Loss for Sentiment Analysis of Code-Mixing Language - Ma, Y., et al. (2020).
• CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP - Qin, L., et al. (2020).
• Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling - Krishnan, J., et al. (2021).
• Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification - Lai, S., et al. (2021).
• Scopa: Soft code-switching and pairwise alignment for zero-shot cross-lingual transfer - Lee, D., et al. (2021).
• Toward the Limitation of Code-Switching in Cross-Lingual Transfer - Feng, Y., et al. (2022).
• ENTITYCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching - Whitehouse, C., et al. (2022).
• Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching - Li, Z., et al. (2024).
• Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction - Sheng, D., et al. (2025).

Text Summarization

• GupShup: Summarizing Open-Domain Code-Switched Conversations - Mehnaz, L., et al. (2021).
• Multilingual Large Language Models Are Not (Yet) Code-Switchers - Zhang, R., et al. (2023).
• CoMix: Guide Transformers to Code-Mix using POS structure and Phonetics - Arora, G., et al. (2023).
• Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation? - Hada, R., et al. (2024).
• CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization - Zhang, R. & Eickhoff, C. (2024).
• Code-Switching Curriculum Learning for Multilingual Transfer in LLMs - Yoo, H., et al. (2025).
• An Adapted Few-Shot Prompting Technique Using ChatGPT to Advance Low-Resource Languages Understanding - Sarrof, Y. R., et al. (2025).

Dialogue Generation

• Detecting Entailment in Code-Mixed Hindi-English Conversations - Sharanya Chakravarthy, et al. (2020).
• A New Dataset for Natural Language Inference from Code-mixed Conversations - Simran Khanuja, et al. (2020).
• Do Multilingual Users Prefer Chat-bots that Code-mix? Let's Nudge and Find Out! - Anshul Bawa, et al. (2020).
• CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP - Libo Qin, et al. (2020).
• Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling - Jitin Krishnan, et al. (2021).
• Towards Code-Mixed Hinglish Dialogue Generation - Vibhav Agarwal, et al. (2021).
• GupShup: Summarizing Open-Domain Code-Switched Conversations - Laiba Mehnaz, et al. (2021).
• Code-switched inspired losses for generic spoken dialog representations - Emile Chapuis, et al. (2021).
• Towards Code-Mixed Hinglish Dialogue Generation - Vibhav Agarwal, et al. (2021).
• MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation - Yongkang Liu, et al. (2022).
• X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents - Mehrad Moradshahi, et al. (2023).
• CST5: Data Augmentation for Code-Switched Semantic Parsing - Agarwal, A., et al. (2023).
• Does a code-switching dialogue system help users learn conversational fluency in Choctaw? - Jacqueline Brixey, et al. (2025).
• Performance Analysis of Effective Retrieval of Kannada Translations in Code-Mixed Sentences using BERT and MPnet - H. P. Rohith, et al. (2025).

Transliteration

• Uncovering Code-Mixed Challenges: A Framework for Linguistically Driven Question Generation and Neural Based Question Answering - Gupta, D., et al. (2018).
• Towards an Efficient Code-Mixed Grapheme-to-Phoneme Conversion in an Agglutinative Language: A Case Study on To-Korean Transliteration - Won Ik Cho, et al. (2020).
• Detecting Entailment in Code-Mixed Hindi-English Conversations - Sharanya Chakravarthy, et al. (2020).
• Graph Convolutional Networks with Multi-headed Attention for Code-Mixed Sentiment Analysis - Dowlagar, S. & Mamidi, R. (2021).
• Normalization and Back-Transliteration for Code-Switched Data - Parikh, D. & Solorio, T. (2021).
• Abusive content detection in transliterated Bengali-English social media corpus - Salim Sazzed (2021).
• Transliteration for Low-Resource Code-Switching Texts: Building an Automatic Cyrillic-to-Latin Converter for Tatar - Taguchi, C., Sakai, Y. & Watanabe, T. (2021).
• MUCS@MixMT: indicTrans-based Machine Translation for Hinglish Text - Asha Hegde, et al. (2022).
• Text Characterization Toolkit (TCT) - Simig, D., et al. (2022).
• Adapting Multilingual Models for Code-Mixed Translation - Vavre, A., Gupta, A. & Sarawagi, S. (2022).
• CodeSwitching and BackTransliteration Using a Bilingual Model - Daniel Weisberg Mitelman, et al. (2024).
• Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs - Arijit Nag, et al. (2024).
• Homophonic Pun Generation in Code Mixed Hindi English - Yash Raj Sarrof (2025).

---

1.3. Underexplored and Frontier Tasks

Unexplored research directions where Code-Switching tasks intersects with reasoning, safety, creativity, and multimodal interaction.

Reasoning & Abstraction

• Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text - Amr Mohamed et al. (2025).
• SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis - Md Nishat Raihan et al. (2023).
• From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences - Prashant Kodali et al. (2025).
• GupShup: Summarizing Open-Domain Code-Switched Conversations - Laiba Mehnaz et al. (2021).

Creative & Code Generation

• CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts - Zhen Yang et al. (2025).
• COCOA: An Encoder-Decoder Model for Controllable Code-switched Generation - Sneha Mondal et al. (2022).
• Can You Translate for Me? Code-Switched Machine Translation with Large Language Models - Jyotsana Khatri et al. (2023).

Conversational & Dialogue systems

• BanglAssist: A Bengali-English Generative AI Chatbot for Code-Switching and Dialect-Handling in Customer Service - Francesco Kruk (2025).
• Does a code-switching dialogue system help users learn conversational fluency in Choctaw? - Jacqueline Brixey et al. (2025).
• X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents - Mehrad Moradshahi et al. (2023).
• Development of a code-switched Hindi-Marathi dataset and transformer-based architecture for enhanced speech recognition - P. Hemant et al. (2025).
• Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues - Kumar, S. & Chakraborty, T. (2024).
• Dialogue Language Model with Large-Scale Persona Data Engineering - Mengze Hong et al. (2025).

Safety & Multimodal

• Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding - Haneul Yoo et al. (2025).
• Tongue-Tied: Breaking LLMs Safety Through New Language Learning - Bibek Upadhayay et al. (2025).
• CM_CLIP: Unveiling Code-Mixed Multimodal Learning with Cross-Lingual CLIP Adaptations - Gitanjali Kumari et al. (2024).
• ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos - Krishanu Maity et al. (2024).
• Multi-task detection of harmful content in code-mixed meme captions using large language models - Bharath Kancharla et al. (2025).
• BanglAssist: A Bengali-English Generative AI Chatbot for Code-Switching and Dialect-Handling in Customer Service - Francesco Kruk (2025).
• Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contexts - Maiya Goloburda, et al. (2025).

2. Datasets & Resources

Corpora, toolkits, and frameworks to support your research.

Datasets

Name	Description	Lang Pair	Type/Task	Link
AfroCS-xs	High-quality human-validated synthetic data.	4 African-En	Machine Translation	🔗
ASCEND	10.6h spontaneous conversational speech.	Mandarin-En	ASR/Dialogue	🔗
BanglishRev	23K Bangla-English reviews for sentiment.	Bengali-En	Sentiment	🔗
CM-DailyDialog	Synthetic code-mixed version of DailyDialog (Hinglish dialogs).	Hindi-En	Dialogue Generation	🔗
CSPref	Human preference dataset for evaluating fluency of LLM-generated code-switched text.	Hindi-En, Tamil-En, Malayalam-En	Preference/Evaluation (LLM-generated CS)	🔗
DravidianCodeMix	~71K code-mixed YouTube comments from Dravidian languages.	Tamil/Kannada/Malayalam-En	Sentiment & Offensive Detection	🔗
GupShup	6.8K+ Hindi-English code-switched conversations with summaries.	Hindi-En	Abstractive Summarization	🔗
HiACC	Hinglish adult & children code-switched corpus.	Hindi-En	Speech/Text	🔗
MMS-5	Multi-scenario multimodal hate speech.	Tamil/Kan-En	MM Hate Speech	🔗
MultiCoNER	Large-scale benchmark for complex NER.	11 Langs	NER	🔗
My Boli	Corpora & Pre-trained Models for Marathi-English.	Marathi-En	NLU	🔗
RideKE	Over 29K code-switched tweets from Kenyan ride-hailing domain.	English-Swahili-Sheng	Sentiment & Emotion	🔗
SCC (Saudilang Code-switch Corpus)	LLM-generated (GPT-4) code-switched speech dataset with Arabic dialects.	Arabic dialects-En/MSA	ASR (Code-Switched)	🔗
SwitchLingua	Massive multi-ethnic code-switching dataset.	83 Langs	General NLU	🔗
ToxVidLM	Framework & dataset for toxicity in code-mixed videos.	Mixed	Video Toxicity	🔗

• Language Modeling for Code-Mixing: The Role of Linguistic Theory based Synthetic Data - Adithya Pratapa, et al. (2018).
• Uncovering Code-Mixed Challenges: A Framework for Linguistically Driven Question Generation and Neural Based Question Answering - Deepak Gupta, et al. (2018).
• Dependency Parser for Bengali-English Code-Mixed Data enhanced with a Synthetic Treebank - Upendra Kumar, et al. (2019).
• Dependency Parsing for English–Malayalam Code-mixed Text - Sanket Sonu, et al. (2019).
• A New Dataset for Natural Language Inference from Code-mixed Conversations - Simran Khanuja, et al. (2020).
• Detecting Entailment in Code-Mixed Hindi-English Conversations - Sharanya Chakravarthy, et al. (2020).
• GupShup: Summarizing Open-Domain Code-Switched Conversations - Laiba Mehnaz, et al. (2021).
• CoMeT: Towards Code-Mixed Translation Using Parallel Monolingual Sentences - Devansh Gautam, et al. (2021).
• Exploring Language Identification from Short Multilingual Code-Switched Texts - Pei-Chi Lo, et al. (2022).
• A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings - Milana Karaica, et al. (2022).
• Code-MixPro: A Framework for Code-Mixed Data Augmentation via Prompt Tuning - Rohit Kundu, et al. (2023).
• OffMix-3L: A Novel Code-Mixed Test Dataset in Bangla-English-Hindi for Offensive Language Identification - Goswami, D., et al. (2023).
• My Boli: A Comprehensive Suite of Corpora and Pre-trained Models for Marathi-English Code-Mixing - Joshi, A., et al. (2023).
• Sentiment Analysis in Code-Mixed Telugu-English Text with Multi-task Learning - Siva Sai, et al. (2024).
• Multilingual Harmful Meme Detection Using Large Language Models - Sanchit Ahuja, et al. (2024).
• Aligning Speech to Languages to Enhance Code-switching Speech Recognition - Hexin Liu, et al. (2024).
• HiACC: Hinglish adult & children code-switched corpus - Singh, S., et al. (2025).
• AfroCS-xs: Creating a Compact, High-Quality, Human-Validated Code-Switched Dataset for African Languages - Olaleye, K., et al. (2025).

Frameworks & Toolkits

• CoSSAT: Code-Switched Speech Annotation Tool - Shah, S., et al. (2019).
• A Unified Framework for Multilingual and Code-Mixed Visual Question Answering - Deepak Gupta, et al. (2020).
• CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing - Jayanthi, S. M., et al. (2021).
• GCM: A Toolkit for Generating Synthetic Code-mixed Text - Rizvi, M. S. Z., et al. (2021).
• Commentator: A Code-mixed Multilingual Text Annotation Framework - Sheth, R., et al. (2024).
• ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos - Krishanu Maity, et al. (2024).
• CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback - Wenbo Zhang (2024).

---

3. Model Training & Adaptation

Techniques for building and adapting models to understand and generate code-mixed language.

Pre-training Approaches

• Modeling Code-Switch Languages Using Bilingual Parallel Corpus - Grandee Lee, et al. (2020).
• SJ AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification - Sai Muralidhar Jayanthi, et al. (2021).
• Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching - Parul Chopra, et al. (2021).
• Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data - Akshat Gupta, et al. (2021).
• Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data - Akshat Gupta, et al. (2021).
• BERTologiCoMix: How does Code-Mixing interact with Multilingual BERT? - Santy, S., et al. (2021).
• HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models - Nayak, R. & Joshi, R. (2022).
• L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Model for Language Identification - Raviraj Joshi, et al. (2022).
• MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation - Kshitij Gupta (2022).
• Transfer Learning for Code-Mixed Data: Do Pretraining Languages Matter? - Kushal Tatariya, et al. (2023).
• Improving Pretraining Techniques for Code-Switched NLP - Richeek Das, et al. (2023).
• Exploring Enhanced Code-Switched Noising for Pretraining in Neural Machine Translation - Vivek Iyer, et al. (2023).
• Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training - Zhijun Wang, et al. (2025).
• Breaking the Language Barrier: Can One Language Model Understand All Languages? - Sanchit Ahuja, et al. (2025).

Fine-tuning Approaches

• From English to Code-Switching: Transfer Learning with Strong Morphological Clues - Gustavo Aguilar, et al. (2020).
• FiSSA at SemEval-2020 Task 9: Fine-tuned for Feelings - Bertelt Braaksma, et al. (2020).
• A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning - Deepak Gupta, et al. (2020).
• A Pre-trained Transformer and CNN model with Joint Language ID and Part-of-Speech Tagging for Code-Mixed Social-Media Text - Suman Dowlagar, et al. (2021).
• The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding - Archiki Prasad, et al. (2021).
• Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification - Siyu Lai, et al. (2021).
• On Utilizing Constituent Language Resources to Improve Downstream Tasks in Hinglish - Vishwajeet Kumar, et al. (2022).
• Adapting Multilingual Models for Code-Mixed Translation - Aditya Vavre, et al. (2022).
• PRO-CS : An Instance-Based Prompt Composition Technique for Code-Switched Tasks - Srijan Bansal, et al. (2022).
• Progressive Sentiment Analysis for Code-Switched Text Data - Sudhanshu Ranjan, et al. (2022).
• ENTITYCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching - Chenxi Whitehouse, et al. (2022).
• COCOA: An Encoder-Decoder Model for Controllable Code-switched Generation - Sneha Mondal, et al. (2022).
• Transfer Learning for Code-Mixed Data: Do Pretraining Languages Matter? - Kushal Tatariya, et al. (2023).
• From Translation to Generative LLMs: Classification of Code-Mixed Affective Tasks - Anjali Yadav, et al. (2024).
• SetFit: A Robust Approach for Offensive Content Detection in Tamil-English Code-Mixed Conversations Using Sentence Transfer Fine-tuning - Kathiravan Pannerselvam, et al. (2024).
• Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation - Kartik, et al. (2024).
• COMMIT: Code-Mixing English-Centric Large Language Model for Multilingual Instruction Tuning - Lee, J., et al. (2024).
• Demystifying Instruction Mixing for Fine-tuning Large Language Models - Wang, R., et al. (2024).
• CHAI for LLMs: Improving Code-Mixed Translation in LLMs through Reinforcement Learning with AI Feedback - Zhang, W., et al. (2025).
• LLMsAgainstHate@NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs - Rushendra Sidibomma, et al. (2025).
• Controlling Language Confusion in Multilingual LLMs - Nahyun Lee, et al. (2025).
• Fine-Tuning Cross-Lingual LLMs for POS Tagging in Code-Switched Contexts - Shayaan Absar (2025).
• Code-Switching Curriculum Learning for Multilingual Transfer in LLMs - Haneul Yoo, et al. (2025).
• MIGRATE: Cross-Lingual Adaptation of Domain-Specific LLMs through Code-Switching and Embedding Transfer - Seongtae Hong, et al. (2025).
• Next-Level Cantonese-to-Mandarin Translation: Fine-Tuning and Post-Processing with LLMs - Yuqian Dai, et al. (2025).
• Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training - Zhijun Wang, et al. (2025).
• Beyond Monolingual Limits: Fine-Tuning Monolingual ASR for Yoruba-English Code-Switching - Oreoluwa Babatunde, et al. (2025).
• Tongue-Tied: Breaking LLMs Safety Through New Language Learning - Bibek Upadhayay, et al. (2025).
• Identifying Aggression and Offensive Language in Code-Mixed Tweets: A Multi-Task Transfer Learning Approach - Bharath Kancharla, et al. (2025).
• Multi-task detection of harmful content in code-mixed meme captions using large language models with zero-shot, few-shot, and fine-tuning approaches - Bharath Kancharla, et al. (2025).
• Adapting Multilingual Models to Code-Mixed Tasks via Model Merging - Sanchit Ahuja, et al. (2025).

Post-training Approaches

• Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification - Siyu Lai, et al. (2021).
• Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling - Jitin Krishnan, et al. (2021).
• PRO-CS : An Instance-Based Prompt Composition Technique for Code-Switched Tasks - Bansal, S., et al. (2022).
• ENTITY CS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching - Chenxi Whitehouse, et al. (2022).
• MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation - Yongkang Liu, et al. (2022).
• MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation - Kshitij Gupta (2022).
• Multilingual Large Language Models Are Not (Yet) Code-Switchers - Ruochen Zhang, et al. (2023).
• Transfer Learning for Code-Mixed Data: Do Pretraining Languages Matter? - Kushal Tatariya, et al. (2023).
• Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages - Zheng-Xin Yong, et al. (2023).
• OffMix-3L: A Novel Code-Mixed Test Dataset in Bangla-English-Hindi for Offensive Language Identification - Dhiman Goswami, et al. (2023).
• Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis - Zeng, L. (2024).
• In-context Mixing (ICM): Code-mixed Prompts for Multilingual LLMs - Shankar, B., et al. (2024).
• From Translation to Generative LLMs: Classification of Code-Mixed Affective Tasks - Anjali Yadav, et al. (2024).
• COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing - Rajvee Sheth, et al. (2025).
• DweshVaani: An LLM for Detecting Religious Hate Speech in Code-Mixed Hindi-English - Varad Srivastava (2025).
• Multi-task detection of harmful content in code-mixed meme captions using large language models with zero-shot, few-shot, and fine-tuning approaches - Bharath Kancharla, et al. (2025).
• An Adapted Few-Shot Prompting Technique Using ChatGPT to Advance Low-Resource Languages Understanding - Yash Raj Sarrof, et al. (2025).

---

4. Evaluation & Benchmarking

Resources for evaluating model performance on code-switching tasks.

📊 Benchmark Comparison

A comparison of major evaluation suites for Code-Switching, categorized by data origin and evaluation focus.

Benchmark	Task Scope	Data Origin	Eval Focus	Link
CodeMixBench	Multitask (LID, POS, NER, SA, MT + Knowledge/Math Reasoning, Truthfulness)	🤖 Synthetic (GPT-assisted)	Multilingual Code-Mixing Capabilities (18 Langs)	🔗
CodeMixBench (Code Gen)	Code Generation (Python)	🧑‍💻 Human (augmented from BigCodeBench)	Syntax & Executability with Code-Mixed Prompts	🔗
COMI-LINGUA	LID, Matrix Language ID, POS, NER, MT	🧑‍💻 Human (expert-annotated)	Multitask NLU & MT in Hindi-English Code-Mixing	🔗
CroCoSum	Cross-lingual Code-switched Summarization	🧑‍💻 Human (English-Hindi dialogues)	Summarization Quality in Code-Switched Context	🔗
CS-Sum	Dialogue Summarization	🧑‍💻 Human (annotated CS dialogues)	Comprehension & Summarization of CS Dialogues	🔗
CS3-Bench	Speech-to-Speech QA & Conversation	🧑‍💻 Human + 🤖 Synthetic	Language Alignment in Mandarin-En CS Speech	🔗
GLUECoS	QA, NLI, Sentiment, LID, POS, NER	🧑‍💻 Human	NLU Performance	🔗
LinCE	LID, NER, POS, Sentiment	🧑‍💻 Human	Linguistic Accuracy (F1)	🔗
Lost in the Mix	Reading Comprehension, Knowledge, NLI	🤖 Synthetic (LLM-generated CS variants)	Deeper Reasoning in Code-Switched Text	🔗
MEGAVERSE	Multimodal QA + Multitask NLU	⚡ Hybrid	Factuality & Robustness (83 Langs)	🔗
PACMAN	POS Tagging	🤖 Synthetic (parallel generation)	POS Accuracy in Code-Mixed Text (Hindi-En focus)	🔗
SwitchLingua	Multitask NLU (83 Langs)	🤖 Hybrid (LLM-synthesized)	Scale & Diversity in Code-Switching	🔗
X-RiSAWOZ	Multilingual Task-Oriented Dialogue (TOD)	🧑‍💻 Human (translated + rewritten)	Cross-lingual TOD in Code-Mixed Scenarios (En-Hi, En-Es, En-Fr)	🔗

(Legend: 🧑‍💻 Human = Manually annotated/curated; 🤖 Synthetic = Generated by Large Language Models; ⚡ Hybrid = Mixed sources or Human-filtered Synthetic data.)

Benchmarks

• LinCE: A centralized benchmark for linguistic code-switching evaluation – Aguilar et al. (2020)
• GLUECoS: An Evaluation Benchmark for Code-Switched NLP – Khanuja et al. (2020)
• PACMAN: Parallel Code-Mixed Data Generation for POS Tagging – Chatterjee et al. (2022)
• MultiCoNER: A Large-scale Multilingual Dataset for Complex NER – Malmasi et al. (2022)
• X-RiSAWOZ: High-Quality Multilingual Dialogue Datasets – Moradshahi et al. (2023)
• CS-Sum: A Benchmark for Code-Switching Dialogue Summarization and the Limits of Large Language Models – Krishnan et al. (2025)
• CroCoSum: Cross-Lingual Code-Switched Summarization Benchmark – Zhang et al. (2024)
• MEGAVERSE: Benchmarking LLMs Across Languages and Tasks – Ahuja et al. (2024)
• COMI-LINGUA: Hindi–English Code-Mixed Multitask Dataset – Sheth et al. (2025)
• CodeMixBench: Code Generation with Code-Mixed Prompts – Sawant (2025)
• SwitchLingua: Large-Scale Multilingual Code-Switching Dataset – Xie (2025)

Evaluation Metrics

• Bleu: a Method for Automatic Evaluation of Machine Translation - Papineni, K., et al. (2002).
• chrF: character n-gram F-score for automatic MT evaluation - Popović, M. (2015).
• Code-Mixing in Social Media Text - Amitava Das, et al. (2013).
• Comparing the Level of Code-Switching in Corpora - Björn Gambäck, et al. (2016).
• Automatic Detection of Code-switching Style from Acoustics - SaiKrishna Rallabandi, et al. (2018).
• Detecting de minimis Code-Switching in Historical German Books - Shijia Liu, et al. (2020).
• Challenges and Limitations with the Metrics Measuring the Complexity of Code-Mixed Text - Vivek Srivastava, et al. (2021).
• SyMCoM - Syntactic Measure of Code Mixing A Study Of English-Hindi Code-Mixing - Prashant Kodali, et al. (2022).
• PreCogIIITH at HinglishEval: Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Quality - Prashant Kodali, et al. (2022).
• Code-Switching Metrics Using Intonation Units - Rebecca Pattichis, et al. (2023).
• Minimal Pair-Based Evaluation of Code-Switching - Sterner, I. & Teufel, S. (2025).
• PIER: A Novel Metric for Evaluating What Matters in Code-Switching - Ugan, E. Y., et al. (2025).
• Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities - Joshi, R., et al. (2025).

---

5. Multi & Cross-Modal Applications

Applying code-switching NLP to speech, vision, and other modalities.

Speech Processing

• ASR

  • Dependency Parsing for English–Malayalam Code-mixed Text - Sanket Sonu, et al. (2019).
  • Semi-supervised Acoustic and Language Model Training for English-isiZulu Code-Switched Speech Recognition - Astik Biswas, et al. (2020).
  • Improving code-switched ASR with linguistic information - Jie Chi, et al. (2022).
  • End-to-End Speech Translation for Code Switched Speech - Orion Weller, et al. (2022).
  • Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation - A. Seza Doğruöz, et al. (2023).
  • New Datasets and Controllable Iterative Data Augmentation Method for Code-switching ASR Error Correction - Zhaohong Wan, et al. (2023).
  • Code-Mixed Text Augmentation for Latvian ASR - Martins Kronis, et al. (2024).
  • The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR - Injy Hamed, et al. (2025).
  • Development of a code-switched Hindi-Marathi dataset and transformer-based architecture for enhanced speech recognition using dynamic switching algorithms - Palash Jain, et al. (2025).
  • ENHANCING ASR ACCURACY AND COHERENCE ACROSS INDIAN LANGUAGES WITH WAV2VEC2 AND GPT - 2 - R. Geetha Rajakumari, et al. (2025).
  • Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM - Yu Xi, et al. (2024).
  • Adapting Whisper for Low-Resource Hindi-English Code-Mix Speech - Sakshi Koli, et al. (2025).

• Speech Translation

  • Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation - Humair Raj Khan, et al. (2021).
  • End-to-End Speech Translation for Code Switched Speech - Weller, O., et al. (2022).
  • CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units - Kang, Y. (2024).
  • Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM - Yu Xi, et al. (2024).
  • The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR - Injy Hamed, et al. (2025).
  • Code-Switching and Syntax: A Large–Scale Experiment - Igor Sterner, et al. (2025).
  • Development of a code-switched Hindi-Marathi dataset and transformer-based architecture for enhanced speech recognition using dynamic switching algorithms - P. Hemant, et al. (2025).
  • ENHANCING ASR ACCURACY AND COHERENCE ACROSS INDIAN LANGUAGES WITH WAV2VEC2 AND GPT - 2 - R. Geetha Rajakumari, et al. (2025).

Vision-Language & Document Processing

• A Unified Framework for Multilingual and Code-Mixed Visual Question Answering - Deepak Gupta, et al. (2020).
• Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation - Raj Khan, H., et al. (2021).
• "To Have the 'Million' Readers Yet": Building a Digitally Enhanced Edition of the Bilingual Irish-English Newspaper - Dereza, O., et al. (2024).
• MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks - Sanchit Ahuja, et al. (2024).
• ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos - Krishanu Maity, et al. (2024).
• Multi-task detection of harmful content in code-mixed meme captions using large language models with zero-shot, few-shot, and fine-tuning approaches - Bharath Kancharla, et al. (2025).
• Enhancing Participatory Development Research in South Asia through LLM Agents System: An Empirically-Grounded Methodological Initiative from Field Evidence in Sri Lankan - Xinjie Zhao, et al. (2025).

Cross-Modal Integration

• Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences - Genta Indra Winata, et al. (2019).
• Translate and Classify: Improving Sequence Level Classification for English-Hindi Code-Mixed Data - Devansh Gautam, et al. (2021).
• Data Augmentation to Address Out of Vocabulary Problem in Low Resource Sinhala English Neural Machine Translation - Aloka Fernando, et al. (2021).
• CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition - Dai, W., et al. (2022).
• Typo-Robust Representation Learning for Dense Retrieval - Panuthep Tasawong, et al. (2023).
• Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising - Tzu Hsuan Chou, et al. (2023).
• ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos - Maity, K., et al. (2024).
• Machine Translation and Transliteration for Indo-Aryan Languages: A Systematic Review - Sandun Sameera Perera, et al. (2025).

---

Workshops & Shared Tasks

A list of academic workshops and community shared tasks dedicated to code-switching.

• First Workshop on Computational Approaches to Code Switching (2014).
• Second Workshop on Computational Approaches to Code Switching (2016).
• CALCS 2018: Workshop on Computational Approaches to Linguistic Code-Switching.
• CALCS 2020: Workshop on Computational Approaches to Linguistic Code-Switching.
• CALCS 2021: Workshop on Computational Approaches to Linguistic Code-Switching.
• DravidianCodeMix Shared Tasks (2020–2021).
• MixMT Shared Task (2022).
• WILDRE-6 2022: Workshop within the 13th Language Resources and Evaluation Conference.
• ICON 2022: 19th International Conference on Natural Language Processing (ICON).
• CALCS 2023: 6th Workshop on Computational Approaches to Linguistic Code-Switching.
• Code-Mixed Sentiment Analysis Shared Task (2024).
• CALCS 2025: 7th Workshop on Computational Approaches to Linguistic Code-Switching.

---

Contributing

Your contributions are always welcome and make this community resource better!

If you have a paper, dataset, or tool you'd like to add:

1. Fork the repository.
2. Add your resource to the relevant section.
3. Please try to follow the existing format and include a direct link.
4. Submit a pull request!