{"total":15,"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":"2403.00393","title":"TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs","created":"2024-03-01","cited_by_count":24,"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":"2506.01840","title":"Minimal Pair-Based Evaluation of Code-Switching","created":"2025-06-02","cited_by_count":8,"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":"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":"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":"2410.12985","title":"Leveraging LLMs for Translating and Classifying Mental Health Data","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2510.12389","title":"Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2409.17397","title":"Building Multilingual Datasets for Predicting Mental Health Severity through LLMs: Prospects and Challenges","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2505.03025","title":"A Typology of Synthetic Datasets for Dialogue Processing in Clinical Contexts","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2607.02235","title":"Challenges and Recommendations for LLM-as-a-Judge in Multilingual Settings and for Low-Resource Languages","created":"2026-07-02","cited_by_count":1,"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":"2609.02391","title":"PolERo: Studying Political Evasion in Romanian","created":"2026-09-02","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}],"next_cursor":null}