{"total":65,"rows":[{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75,"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":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"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":"2406.15481","title":"Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding","created":"2024-06-17","cited_by_count":34,"area":"safety"},{"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":"2505.14815","title":"Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2410.12656","title":"Evaluating Morphological Compositional Generalization in Large Language Models","created":"2024-10-16","cited_by_count":19,"area":null},{"id":"2309.05454","title":"Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models","created":"2023-09-11","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":"2402.14714","title":"Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models","created":"2024-02-22","cited_by_count":15,"area":null},{"id":"2402.12976","title":"The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2310.03018","title":"Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2402.13109","title":"CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models","created":"2024-02-20","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":"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":"2509.23659","title":"Aligning LLMs for Multilingual Consistency in Enterprise Applications","created":"2025-09-28","cited_by_count":11,"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":"2507.20395","title":"MazeEval: A Benchmark for Testing Sequential Decision-Making in Language Models","created":"2025-07-27","cited_by_count":8,"area":"lr"},{"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":"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":"2404.09138","title":"From Bytes to Borsch: Fine-Tuning Gemma and Mistral for the Ukrainian Language Representation","created":"2024-04-14","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":"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":"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":"2410.18836","title":"From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2411.09073","title":"CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback","created":"2024-11-13","cited_by_count":5,"area":"alignment"},{"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":"2602.16201","title":"Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2405.12929","title":"Code-mixed Sentiment and Hate-speech Prediction","created":"2024-05-21","cited_by_count":4,"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":"2602.11174","title":"The Script Tax: Measuring Tokenization-Driven Efficiency and Latency Disparities in Multilingual Language Models","created":"2026-01-19","cited_by_count":4,"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":"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":"2601.03589","title":"OLA: Output Language Alignment in Code-Switched LLM Interactions","created":"2026-01-07","cited_by_count":3,"area":"alignment"},{"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":"2505.12587","title":"CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling","created":"2025-05-19","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":"2505.20445","title":"In-context Language Learning for Endangered Languages in Speech Recognition","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.04385","title":"MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.12744","title":"Rethinking Hate Speech Detection on Social Media: Can LLMs Replace Traditional Models?","created":"2025-06-15","cited_by_count":2,"area":"lr"},{"id":"2507.14894","title":"SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs","created":"2025-07-20","cited_by_count":2,"area":"mechinterp"},{"id":"2312.13179","title":"Contextual Code Switching for Machine Translation using Language Models","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2407.14295","title":"CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units","created":"2024-07-19","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":"2511.10670","title":"Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment","created":"2025-11-09","cited_by_count":1,"area":"moe"},{"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":"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":"2502.07058","title":"Using Contextually Aligned Online Reviews to Measure LLMs' Performance Disparities Across Language Varieties","created":"2025-02-10","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":"2510.01616","title":"Efficient Training of Robust Traditional Chinese LLaMA-1B on a Single Consumer GPU: Continual Pre-training, SFT, and DPO","created":"2025-10-02","cited_by_count":0,"area":"alignment"},{"id":"2510.11076","title":"DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education","created":"2025-10-13","cited_by_count":0,"area":"agents"},{"id":"2512.03334","title":"Modeling Topics and Sociolinguistic Variation in Code-Switched Discourse: Insights from Spanish-English and Spanish-Guaran\\'i","created":"2025-12-03","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":"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":"2605.07132","title":"From Standard English to Singlish: A Retrieval-Augmented Approach for Code-Switched Creole Generation in Large Language Models","created":"2026-05-08","cited_by_count":0,"area":"rag"},{"id":"2606.06037","title":"SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech","created":"2026-06-04","cited_by_count":0,"area":"alignment"},{"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":"2606.22361","title":"First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.25380","title":"A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2609.14571","title":"Domain-specific Pretraining Profile and Transformer Performance: Evidence from Modeling Digital Pragmatics in Arabic-English Code-switching","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}