{"total":97,"rows":[{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168,"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":"2401.01055","title":"LLaMA Beyond English: An Empirical Study on Language Capability Transfer","created":"2024-01-02","cited_by_count":95,"area":null},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75,"area":null},{"id":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"area":null},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68,"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":"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":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","cited_by_count":56,"area":null},{"id":"2404.16816","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","created":"2024-04-25","cited_by_count":56,"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":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50,"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":"2204.08398","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models","created":"2022-04-18","cited_by_count":34,"area":null},{"id":"2107.06483","title":"From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text","created":"2021-07-14","cited_by_count":29,"area":null},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2103.09593","title":"Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2402.14700","title":"Unveiling Linguistic Regions in Large Language Models","created":"2024-02-22","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":"2110.07385","title":"Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings","created":"2021-10-14","cited_by_count":21,"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":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"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":"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":"2406.07424","title":"MINERS: Multilingual Language Models as Semantic Retrievers","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2108.12465","title":"Code-switched inspired losses for generic spoken dialog representations","created":"2021-08-27","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":"2106.06004","title":"CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing","created":"2021-06-10","cited_by_count":8,"area":null},{"id":"2210.12540","title":"EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching","created":"2022-10-22","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":"2505.16538","title":"Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models","created":"2025-05-22","cited_by_count":8,"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":"2305.16724","title":"Code-Switched Text Synthesis in Unseen Language Pairs","created":"2023-05-26","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":"2111.01340","title":"Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks","created":"2021-11-02","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":"2311.12405","title":"IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages","created":"2023-11-21","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":"2107.01202","title":"Language Identification of Hindi-English tweets using code-mixed BERT","created":"2021-07-02","cited_by_count":4,"area":null},{"id":"2109.00475","title":"Capturing Stance Dynamics in Social Media: Open Challenges and Research Directions","created":"2021-09-01","cited_by_count":4,"area":null},{"id":"2109.07140","title":"On the Universality of Deep Contextual Language Models","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","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":"2503.04797","title":"Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2505.20875","title":"Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2101.09004","title":"CMSAOne@Dravidian-CodeMix-FIRE2020: A Meta Embedding and Transformer model for Code-Mixed Sentiment Analysis on Social Media Text","created":"2021-01-22","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":"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":"2505.18927","title":"Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments","created":"2025-05-25","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":"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":"2110.12780","title":"Battling Hateful Content in Indic Languages HASOC '21","created":"2021-10-25","cited_by_count":1,"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":"2210.14380","title":"Progressive Sentiment Analysis for Code-Switched Text Data","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2305.14534","title":"Detecting Propaganda Techniques in Code-Switched Social Media Text","created":"2023-05-23","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":"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":"2510.19782","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":"2105.09226","title":"Detection of Emotions in Hindi-English Code Mixed Text Data","created":"2021-05-19","cited_by_count":0,"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":"2206.07988","title":"PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Quality","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2305.09520","title":"DLUE: Benchmarking Document Language Understanding","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2306.04964","title":"Leveraging Language Identification to Enhance Code-Mixed Text Classification","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2407.10582","title":"Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selection","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2506.23122","title":"Decoding Memes: Benchmarking Narrative Role Classification across Multilingual and Multimodal Models","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2508.14051","title":"Benchmarking Sociolinguistic Diversity in Swahili NLP: A Taxonomy-Guided Approach","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.02514","title":"Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognition","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2509.23197","title":"Global Beats, Local Tongue: Studying Code Switching in K-pop Hits on Billboard Charts","created":"2025-09-27","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":"2602.15373","title":"Far Out: Evaluating Language Models on Slang in Australian and Indian English","created":"2026-02-17","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":"2609.06963","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":"2609.09356","title":"Auditable Emergency Triage for Maternal and Newborn Care in India","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.09964","title":"5-Dialects-BN: Unmasking the Impact of Transliteration on Bangla Dialectal LLMs","created":"2026-09-09","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":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","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}