{"total":28,"rows":[{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2411.02460","title":"Code-Switching Curriculum Learning for Multilingual Transfer in LLMs","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24,"area":null},{"id":"2205.12676","title":"Evaluating the Diversity, Equity and Inclusion of NLP Technology: A Case Study for Indian Languages","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2106.10123","title":"Challenges and Limitations with the Metrics Measuring the Complexity of Code-Mixed Text","created":"2021-06-18","cited_by_count":18,"area":null},{"id":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2212.03419","title":"JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset","created":"2022-12-07","cited_by_count":11,"area":null},{"id":"2507.18791","title":"CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages","created":"2025-07-24","cited_by_count":10,"area":null},{"id":"2107.11534","title":"MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluation","created":"2021-07-24","cited_by_count":7,"area":null},{"id":"2301.08937","title":"Exploring Methods for Building Dialects-Mandarin Code-Mixing Corpora: A Case Study in Taiwanese Hokkien","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2503.21670","title":"COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing","created":"2025-03-27","cited_by_count":7,"area":null},{"id":"2104.08578","title":"GupShup: An Annotated Corpus for Abstractive Summarization of Open-Domain Code-Switched Conversations","created":"2021-04-17","cited_by_count":5,"area":null},{"id":"2510.07037","title":"Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2107.09931","title":"The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2206.07318","title":"CMNEROne at SemEval-2022 Task 11: Code-Mixed Named Entity Recognition by leveraging multilingual data","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2405.12929","title":"Code-mixed Sentiment and Hate-speech Prediction","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2201.11391","title":"Prabhupadavani: A Code-mixed Speech Translation Data for 25 Languages","created":"2022-01-27","cited_by_count":2,"area":null},{"id":"2302.11766","title":"MUTANT: A Multi-sentential Code-mixed Hinglish Dataset","created":"2023-02-23","cited_by_count":2,"area":null},{"id":"2309.16202","title":"Marathi-English Code-mixed Text Generation","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2212.08565","title":"Automatic Identification of Motivation for Code-Switching in Speech Transcripts","created":"2022-11-30","cited_by_count":1,"area":null},{"id":"2308.08807","title":"Linguistically-Informed Neural Architectures for Lexical, Syntactic and Semantic Tasks in Sanskrit","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2403.01364","title":"Improving Cross-lingual Representation for Semantic Retrieval with Code-switching","created":"2024-03-03","cited_by_count":1,"area":null},{"id":"2605.00116","title":"ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2304.01423","title":"Thematic context vector association based on event uncertainty for Twitter","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2504.21026","title":"Creating and Evaluating Code-Mixed Nepali-English and Telugu-English Datasets for Abusive Language Detection Using Traditional and Deep Learning Models","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2506.00332","title":"Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus","created":"2025-05-31","cited_by_count":0,"area":null}],"next_cursor":null}