{"list":"other","total":55,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214},{"id":"2005.09093","title":"Are All Languages Created Equal in Multilingual BERT?","created":"2020-05-18","cited_by_count":207},{"id":"2304.05613","title":"ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning","created":"2023-04-12","cited_by_count":206},{"id":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"2305.16307","title":"IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages","created":"2023-05-25","cited_by_count":152},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148},{"id":"2102.00894","title":"Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models","created":"2021-02-01","cited_by_count":132},{"id":"2010.06189","title":"X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models","created":"2020-10-13","cited_by_count":117},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57},{"id":"2005.04816","title":"Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation","created":"2020-05-11","cited_by_count":51},{"id":"2306.11372","title":"Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts","created":"2023-06-20","cited_by_count":45},{"id":"2001.09907","title":"PMIndia -- A Collection of Parallel Corpora of Languages of India","created":"2020-01-27","cited_by_count":42},{"id":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","cited_by_count":42},{"id":"2205.11081","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","created":"2022-05-23","cited_by_count":42},{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35},{"id":"2311.05845","title":"Tamil-Llama: A New Tamil Language Model Based on Llama 2","created":"2023-11-10","cited_by_count":32},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27},{"id":"2204.08776","title":"IndicXNLI: Evaluating Multilingual Inference for Indian Languages","created":"2022-04-19","cited_by_count":26},{"id":"2404.13506","title":"Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications","created":"2024-04-21","cited_by_count":25},{"id":"2009.12534","title":"iNLTK: Natural Language Toolkit for Indic Languages","created":"2020-09-26","cited_by_count":24},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24},{"id":"2309.13173","title":"BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP","created":"2023-09-22","cited_by_count":23},{"id":"2011.02323","title":"Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages","created":"2020-11-04","cited_by_count":22},{"id":"2401.10521","title":"Cross-lingual Editing in Multilingual Language Models","created":"2024-01-19","cited_by_count":18},{"id":"2205.00328","title":"HateCheckHIn: Evaluating Hindi Hate Speech Detection Models","created":"2022-04-30","cited_by_count":15},{"id":"2306.08133","title":"Large-scale Language Model Rescoring on Long-form Data","created":"2023-06-13","cited_by_count":14},{"id":"2403.02370","title":"adaptMLLM: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated LLM Playgrounds","created":"2024-03-04","cited_by_count":14},{"id":"2312.12624","title":"Building a Llama2-finetuned LLM for Odia Language Utilizing Domain Knowledge Instruction Set","created":"2023-12-19","cited_by_count":12},{"id":"2403.04792","title":"Breaking the Language Barrier: Can Direct Inference Outperform Pre-Translation in Multilingual LLM Applications?","created":"2024-03-04","cited_by_count":12},{"id":"2307.07422","title":"Can LLMs be Good Financial Advisors?: An Initial Study in Personal Decision Making for Optimized Outcomes","created":"2023-07-08","cited_by_count":11},{"id":"2310.18205","title":"Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media","created":"2023-10-27","cited_by_count":8},{"id":"2311.09216","title":"Assessing Translation capabilities of Large Language Models involving English and Indian Languages","created":"2023-11-15","cited_by_count":8},{"id":"2305.03300","title":"LLM-RM at SemEval-2023 Task 2: Multilingual Complex NER using XLM-RoBERTa","created":"2023-05-05","cited_by_count":7},{"id":"2006.01432","title":"BERT Based Multilingual Machine Comprehension in English and Hindi","created":"2020-06-02","cited_by_count":5},{"id":"2404.03528","title":"BanglaAutoKG: Automatic Bangla Knowledge Graph Construction with Semantic Neural Graph Filtering","created":"2024-04-04","cited_by_count":5},{"id":"2107.01202","title":"Language Identification of Hindi-English tweets using code-mixed BERT","created":"2021-07-02","cited_by_count":4},{"id":"2309.10272","title":"Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi","created":"2023-09-19","cited_by_count":4},{"id":"2401.13085","title":"IndiText Boost: Text Augmentation for Low Resource India Languages","created":"2024-01-23","cited_by_count":4},{"id":"2310.10935","title":"Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti","created":"2023-10-17","cited_by_count":3},{"id":"2311.02570","title":"BanMANI: A Dataset to Identify Manipulated Social Media News in Bangla","created":"2023-11-05","cited_by_count":3},{"id":"2205.11976","title":"Universal Dependency Treebank for Odia Language","created":"2022-05-24","cited_by_count":2},{"id":"2307.15376","title":"Multilingual Tourist Assistance using ChatGPT: Comparing Capabilities in Hindi, Telugu, and Kannada","created":"2023-07-28","cited_by_count":2},{"id":"2309.11165","title":"Assessment of Pre-Trained Models Across Languages and Grammars","created":"2023-09-20","cited_by_count":2},{"id":"2304.13005","title":"Evaluating Inter-Bilingual Semantic Parsing for Indian Languages","created":"2023-04-25","cited_by_count":1},{"id":"2402.14179","title":"Bangla AI: A Framework for Machine Translation Utilizing Large Language Models for Ethnic Media","created":"2024-02-21","cited_by_count":1}],"next_cursor":null}