{"total":44,"rows":[{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75,"area":null},{"id":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73,"area":null},{"id":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","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":"2406.08818","title":"Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination","created":"2024-06-13","cited_by_count":56,"area":null},{"id":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27,"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":"2305.13627","title":"InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning","created":"2023-05-23","cited_by_count":21,"area":null},{"id":"2401.01596","title":"MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries","created":"2024-01-03","cited_by_count":19,"area":null},{"id":"2311.09071","title":"How Vocabulary Sharing Facilitates Multilingualism in LLaMA?","created":"2023-11-15","cited_by_count":12,"area":null},{"id":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","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":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2410.11079","title":"Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities","created":"2024-10-14","cited_by_count":7,"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":"2508.19089","title":"It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs","created":"2025-08-26","cited_by_count":6,"area":null},{"id":"2309.10661","title":"NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages","created":"2023-09-19","cited_by_count":5,"area":null},{"id":"2310.08885","title":"InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems","created":"2023-10-13","cited_by_count":5,"area":null},{"id":"2406.08726","title":"Standard Language Ideology in AI-Generated Language","created":"2024-06-13","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":"2410.21573","title":"Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense","created":"2024-10-28","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":"2309.02915","title":"Persona-aware Generative Model for Code-mixed Language","created":"2023-09-06","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":"2309.16202","title":"Marathi-English Code-mixed Text Generation","created":"2023-09-28","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":"2508.12662","title":"Breaking Language Barriers: Equitable Performance in Multilingual Language Models","created":"2025-08-18","cited_by_count":2,"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":"2601.17277","title":"PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues","created":"2026-01-24","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":"2411.04308","title":"Improving Bilingual Capabilities of Language Models to Support Diverse Linguistic Practices in Education","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2505.16631","title":"MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries","created":"2025-05-22","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},{"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":"2602.15866","title":"NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey","created":"2026-01-26","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}