{"total":56,"rows":[{"id":"2305.18365","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","created":"2023-05-27","cited_by_count":185,"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":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"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":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"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":"2112.06223","title":"ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation","created":"2021-12-12","cited_by_count":44,"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":"2105.03953","title":"Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation","created":"2021-05-09","cited_by_count":29,"area":null},{"id":"2204.05076","title":"End-to-End Speech Translation for Code Switched Speech","created":"2022-04-11","cited_by_count":26,"area":null},{"id":"2111.09453","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","created":"2021-11-18","cited_by_count":22,"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":"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":"2303.17322","title":"Yes but.. Can ChatGPT Identify Entities in Historical Documents?","created":"2023-03-30","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":"2303.04092","title":"CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization","created":"2023-03-07","cited_by_count":8,"area":null},{"id":"2108.01861","title":"Quality Evaluation of the Low-Resource Synthetically Generated Code-Mixed Hinglish Text","created":"2021-08-04","cited_by_count":7,"area":null},{"id":"2203.08979","title":"Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2403.17556","title":"m3P: Towards Multimodal Multilingual Translation with Multimodal Prompt","created":"2024-03-26","cited_by_count":6,"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":"2108.10808","title":"Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation","created":"2021-08-24","cited_by_count":5,"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":"2204.06699","title":"SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study","created":"2022-04-14","cited_by_count":5,"area":null},{"id":"2209.01638","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","created":"2022-09-04","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":"2410.18836","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":"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":"2104.06268","title":"Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling","created":"2021-04-13","cited_by_count":4,"area":null},{"id":"2107.09931","title":"The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2310.12648","title":"Towards Real-World Streaming Speech Translation for Code-Switched Speech","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2310.15258","title":"Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention","created":"2023-10-23","cited_by_count":4,"area":"lr"},{"id":"2405.12929","title":"Code-mixed Sentiment and Hate-speech Prediction","created":"2024-05-21","cited_by_count":4,"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":"2109.14350","title":"Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Models","created":"2021-09-29","cited_by_count":2,"area":null},{"id":"2402.03642","title":"Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation","created":"2024-02-06","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":"2503.11911","title":"LAG-MMLU: Benchmarking Frontier LLM Understanding in Latvian and Giriama","created":"2025-03-14","cited_by_count":2,"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":"2212.08054","title":"DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2212.08565","title":"Automatic Identification of Motivation for Code-Switching in Speech Transcripts","created":"2022-11-30","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":"2506.02527","title":"Multilingual Information Retrieval with a Monolingual Knowledge Base","created":"2025-06-03","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":"2210.05487","title":"Like a bilingual baby: The advantage of visually grounding a bilingual language model","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2210.16461","title":"Sentiment Classification of Code-Switched Text using Pre-trained Multilingual Embeddings and Segmentation","created":"2022-10-29","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2603.16184","title":"Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR","created":"2026-03-17","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":"2606.21869","title":"The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference","created":"2026-06-20","cited_by_count":0,"area":null}],"next_cursor":null}