{"list":"other","total":78,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293},{"id":"2402.10588","title":"Do Llamas Work in English? On the Latent Language of Multilingual Transformers","created":"2024-02-16","cited_by_count":281},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278},{"id":"2004.11867","title":"Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation","created":"2020-04-24","cited_by_count":277},{"id":"2310.08319","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","created":"2023-10-12","cited_by_count":272},{"id":"1908.11828","title":"PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification","created":"2019-08-30","cited_by_count":264},{"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":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204},{"id":"2307.16039","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","created":"2023-07-29","cited_by_count":190},{"id":"1911.01464","title":"Emerging Cross-lingual Structure in Pretrained Language Models","created":"2019-11-04","cited_by_count":181},{"id":"2010.03093","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","created":"2020-10-07","cited_by_count":154},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153},{"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":"2402.18815","title":"How do Large Language Models Handle Multilingualism?","created":"2024-02-29","cited_by_count":150},{"id":"2310.20707","title":"What's In My Big Data?","created":"2023-10-31","cited_by_count":129},{"id":"2002.03518","title":"Multilingual Alignment of Contextual Word Representations","created":"2020-02-10","cited_by_count":114},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110},{"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":"1909.00964","title":"Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks","created":"2019-09-03","cited_by_count":96},{"id":"2402.11548","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","created":"2024-02-18","cited_by_count":91},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88},{"id":"2307.16645","title":"Scaling Sentence Embeddings with Large Language Models","created":"2023-07-31","cited_by_count":85},{"id":"2101.11109","title":"First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT","created":"2021-01-26","cited_by_count":65},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57},{"id":"2407.03211","title":"How Does Quantization Affect Multilingual LLMs?","created":"2024-07-03","cited_by_count":43},{"id":"2401.07817","title":"Question Translation Training for Better Multilingual Reasoning","created":"2024-01-15","cited_by_count":42},{"id":"2408.10811","title":"Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?","created":"2024-08-20","cited_by_count":41},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39},{"id":"2312.12683","title":"Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?","created":"2023-12-20","cited_by_count":39},{"id":"2404.11553","title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","created":"2024-04-17","cited_by_count":38},{"id":"2404.06228","title":"Understanding Cross-Lingual Alignment -- A Survey","created":"2024-04-09","cited_by_count":34},{"id":"1905.06401","title":"Correlating neural and symbolic representations of language","created":"2019-05-14","cited_by_count":33},{"id":"2311.08089","title":"Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment","created":"2023-11-14","cited_by_count":33},{"id":"2407.12402","title":"TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish","created":"2024-07-17","cited_by_count":32},{"id":"2406.16235","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","created":"2024-06-23","cited_by_count":31},{"id":"2306.06688","title":"Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability","created":"2023-06-11","cited_by_count":27},{"id":"2204.08776","title":"IndicXNLI: Evaluating Multilingual Inference for Indian Languages","created":"2022-04-19","cited_by_count":26},{"id":"2110.04504","title":"An Isotropy Analysis in the Multilingual BERT Embedding Space","created":"2021-10-09","cited_by_count":25},{"id":"2009.14304","title":"Cross-lingual Alignment Methods for Multilingual BERT: A Comparative Study","created":"2020-09-29","cited_by_count":24},{"id":"2305.06897","title":"AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages","created":"2023-05-11","cited_by_count":23},{"id":"2404.06644","title":"Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?","created":"2024-04-09","cited_by_count":22},{"id":"2406.14670","title":"Exploring Design Choices for Building Language-Specific LLMs","created":"2024-06-20","cited_by_count":22},{"id":"2407.16222","title":"PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment","created":"2024-07-23","cited_by_count":20},{"id":"2306.00458","title":"Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity","created":"2023-06-01","cited_by_count":17},{"id":"2309.13320","title":"GlotScript: A Resource and Tool for Low Resource Writing System Identification","created":"2023-09-23","cited_by_count":15},{"id":"2409.14459","title":"Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis","created":"2024-09-22","cited_by_count":12},{"id":"2404.07982","title":"The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments","created":"2024-04-11","cited_by_count":9},{"id":"2409.17326","title":"How Transliterations Improve Crosslingual Alignment","created":"2024-09-25","cited_by_count":6},{"id":"2204.06457","title":"The Impact of Cross-Lingual Adjustment of Contextual Word Representations on Zero-Shot Transfer","created":"2022-04-13","cited_by_count":5},{"id":"2304.08205","title":"VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning","created":"2023-04-17","cited_by_count":3}],"next_cursor":null}