{"total":51,"rows":[{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75,"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":"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":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"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":"2406.06263","title":"MaskLID: Code-Switching Language Identification through Iterative Masking","created":"2024-06-10","cited_by_count":11,"area":null},{"id":"2501.09512","title":"PIER: A Novel Metric for Evaluating What Matters in Code-Switching","created":"2025-01-16","cited_by_count":11,"area":null},{"id":"2403.18182","title":"ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus","created":"2024-03-27","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":"2303.04092","title":"CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization","created":"2023-03-07","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":"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":"2405.11125","title":"A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base","created":"2024-05-17","cited_by_count":7,"area":null},{"id":"2406.00343","title":"Beyond Metrics: Evaluating LLMs' Effectiveness in Culturally Nuanced, Low-Resource Real-World Scenarios","created":"2024-06-01","cited_by_count":7,"area":null},{"id":"2404.19442","title":"Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs","created":"2024-04-30","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":"2311.08348","title":"MC$^2$: Towards Transparent and Culturally-Aware NLP for Minority Languages in China","created":"2023-11-14","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":"2310.15262","title":"Data Augmentation Techniques for Machine Translation of Code-Switched Texts: A Comparative Study","created":"2023-10-23","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":"2404.17216","title":"Prompting Towards Alleviating Code-Switched Data Scarcity in Under-Resourced Languages with GPT as a Pivot","created":"2024-04-26","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":"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":"2510.05678","title":"Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2305.02637","title":"Towards Weakly-Supervised Hate Speech Classification Across Datasets","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2404.12489","title":"Grammatical Error Correction for Code-Switched Sentences by Learners of English","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2412.12761","title":"Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2510.18724","title":"Adapting Language Balance in Code-Switching Speech","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2402.03137","title":"Sociolinguistically Informed Interpretability: A Case Study on Hinglish Emotion Classification","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2403.04639","title":"MaCmS: Magahi Code-mixed Dataset for Sentiment Analysis","created":"2024-03-07","cited_by_count":1,"area":null},{"id":"2503.23576","title":"The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR","created":"2025-03-30","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":"2506.02527","title":"Multilingual Information Retrieval with a Monolingual Knowledge Base","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2510.18723","title":"Bayesian Low-Rank Factorization for Robust Model Adaptation","created":"2025-10-21","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":"2605.27649","title":"Disentangling Language Roles in Multilingual LLM Task Execution","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.19381","title":"Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2606.19668","title":"Code-Switching Reveals Language Anchoring in Multilingual LLMs","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2410.11230","title":"\"Is Hate Lost in Translation?\": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2504.20051","title":"Evaluating Large Language Models on Multiword Expressions in Multilingual and Code-Switched Contexts","created":"2025-04-10","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":"2602.13123","title":"From sunblock to softblock: Analyzing the correlates of neology in published writing and on social media","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2602.15866","title":"NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.07366","title":"RILEC: Detection and Generation of L1 Russian Interference Errors in English Learner Texts","created":"2026-03-07","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":"2609.35645","title":"CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01450","title":"Code-Switching Spoken Language Identification as Multi-Label Set Prediction","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}