{"total":89,"rows":[{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2305.14235","title":"Multilingual Large Language Models Are Not (Yet) Code-Switchers","created":"2023-05-23","cited_by_count":65,"area":null},{"id":"2301.01967","title":"A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies","created":"2023-01-05","cited_by_count":59,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"area":null},{"id":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","cited_by_count":56,"area":null},{"id":"2207.06991","title":"Language Modelling with Pixels","created":"2022-07-14","cited_by_count":55,"area":null},{"id":"2303.13592","title":"Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages","created":"2023-03-23","cited_by_count":51,"area":null},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39,"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":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2111.09453","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","created":"2021-11-18","cited_by_count":22,"area":null},{"id":"2105.04846","title":"Can You Traducir This? Machine Translation for Code-Switched Input","created":"2021-05-11","cited_by_count":21,"area":null},{"id":"2208.07864","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","created":"2022-08-16","cited_by_count":16,"area":null},{"id":"2204.10815","title":"A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task Learning","created":"2022-04-22","cited_by_count":12,"area":null},{"id":"2204.13743","title":"HiNER: A Large Hindi Named Entity Recognition Dataset","created":"2022-04-28","cited_by_count":12,"area":null},{"id":"2409.19505","title":"The Nature of NLP: Analyzing Contributions in NLP Papers","created":"2024-09-29","cited_by_count":12,"area":null},{"id":"2102.01051","title":"SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification","created":"2021-02-01","cited_by_count":11,"area":null},{"id":"2406.06263","title":"MaskLID: Code-Switching Language Identification through Iterative Masking","created":"2024-06-10","cited_by_count":11,"area":null},{"id":"2406.07424","title":"MINERS: Multilingual Language Models as Semantic Retrievers","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2303.17322","title":"Yes but.. Can ChatGPT Identify Entities in Historical Documents?","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2506.14012","title":"Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text","created":"2025-06-16","cited_by_count":10,"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":"2106.09462","title":"pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks","created":"2021-06-17","cited_by_count":9,"area":null},{"id":"2202.09625","title":"CALCS 2021 Shared Task: Machine Translation for Code-Switched Data","created":"2022-02-19","cited_by_count":9,"area":null},{"id":"2106.06004","title":"CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing","created":"2021-06-10","cited_by_count":8,"area":null},{"id":"2303.04092","title":"CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization","created":"2023-03-07","cited_by_count":8,"area":null},{"id":"2405.05572","title":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2103.03494","title":"Stratified Sampling for Extreme Multi-Label Data","created":"2021-03-05","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2403.04872","title":"Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text","created":"2024-03-07","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":"2102.12700","title":"Sentiment Analysis of Persian-English Code-mixed Texts","created":"2021-02-25","cited_by_count":6,"area":null},{"id":"2109.08607","title":"The futility of STILTs for the classification of lexical borrowings in Spanish","created":"2021-09-17","cited_by_count":6,"area":null},{"id":"2203.16169","title":"Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling","created":"2022-03-30","cited_by_count":6,"area":null},{"id":"2410.22660","title":"Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2505.11665","title":"Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2111.01231","title":"Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2206.04973","title":"Borrowing or Codeswitching? Annotating for Finer-Grained Distinctions in Language Mixing","created":"2022-06-10","cited_by_count":5,"area":null},{"id":"2309.06163","title":"Overview of GUA-SPA at IberLEF 2023: Guarani-Spanish Code Switching Analysis","created":"2023-09-12","cited_by_count":5,"area":null},{"id":"2311.12405","title":"IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages","created":"2023-11-21","cited_by_count":5,"area":null},{"id":"2403.16771","title":"Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2410.18436","title":"Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2501.13419","title":"A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions","created":"2025-01-23","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":"2106.07823","title":"Challenges and Considerations with Code-Mixed NLP for Multilingual Societies","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2112.03154","title":"VAE based Text Style Transfer with Pivot Words Enhancement Learning","created":"2021-12-06","cited_by_count":4,"area":null},{"id":"2411.00691","title":"Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2507.21813","title":"Overview of ADoBo at IberLEF 2025: Automatic Detection of Anglicisms in Spanish","created":"2025-07-29","cited_by_count":4,"area":null},{"id":"2204.05232","title":"Survey of Aspect-based Sentiment Analysis Datasets","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2402.01505","title":"Code-Switched Language Identification is Harder Than You Think","created":"2024-02-02","cited_by_count":3,"area":null},{"id":"2410.10580","title":"Multilingual Controlled Generation And Gold-Standard-Agnostic Evaluation of Code-Mixed Sentences","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2502.12924","title":"Conditioning LLMs to Generate Code-Switched Text","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2503.20007","title":"Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2509.17768","title":"DIVERS-Bench: Evaluating Language Identification Across Domain Shifts and Code-Switching","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2109.14350","title":"Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Models","created":"2021-09-29","cited_by_count":2,"area":null},{"id":"2410.16221","title":"On Creating an English-Thai Code-switched Machine Translation in Medical Domain","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2505.13559","title":"CS-Sum: A Benchmark for Code-Switching Dialogue Summarization and the Limits of Large Language Models","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2506.07274","title":"Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2508.12662","title":"Breaking Language Barriers: Equitable Performance in Multilingual Language Models","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2202.02702","title":"How Effective is Incongruity? Implications for Code-mix Sarcasm Detection","created":"2022-02-06","cited_by_count":1,"area":null},{"id":"2204.10185","title":"Social Media Sentiment Analysis for Cryptocurrency Market Prediction","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2212.08054","title":"DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2308.15209","title":"Shared Lexical Items as Triggers of Code Switching","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2309.05044","title":"The Effect of Alignment Objectives on Code-Switching Translation","created":"2023-09-10","cited_by_count":1,"area":null},{"id":"2410.13318","title":"Computational Approaches to Arabic-English Code-Switching","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2503.07990","title":"Enhancing Multilingual Language Models for Code-Switched Input Data","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2505.24472","title":"VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2510.13849","title":"Language steering in latent space to mitigate unintended code-switching","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2510.19782","title":"Adapting Multilingual Models to Code-Mixed Tasks via Model Merging","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.17277","title":"PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2603.10789","title":"LuxBorrow: From Pompier to Pompjee, Tracing Borrowing in Luxembourgish","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.27649","title":"Disentangling Language Roles in Multilingual LLM Task Execution","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2205.00868","title":"TuGeBiC: A Turkish German Bilingual Code-Switching Corpus","created":"2022-05-02","cited_by_count":0,"area":null},{"id":"2505.11746","title":"Token Masking Improves Transformer-Based Text Classification","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2510.19585","title":"Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2601.16217","title":"ChiEngMixBench: Evaluating Large Language Models on Expert-Style Chinese-English Terminology Mixing","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2602.11181","title":"Code Mixologist : A Practitioner's Guide to Building Code-Mixed LLMs","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.11358","title":"Multilingual Financial Fraud Detection Using Machine Learning and Transformer Models: A Bangla-English Study","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.19771","title":"Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text in Multilingual Encoders","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.26587","title":"EnTaCs: Analyzing the Relationship Between Sentiment and Language Choice in English-Tamil Code-Switching","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2606.13537","title":"When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.30790","title":"Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.26434","title":"AfriSwitch: A Benchmark for In-the-Wild African Code-Switched Speech Recognition","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.05099","title":"Improving Language Identification for Code-Switched Utterances with Integer Linear Programming","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.06963","title":"TurEngMix: A Text Corpus and Benchmark for Turkish-English Code-Mixed Language Identification and Named Entity Recognition","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.22138","title":"Does the Truthfulness Signal Survive Code-Mixing? Probing Hidden States for Hallucination Detection in Hinglish","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2610.20272","title":"CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}