{"list":"other","total":54,"rows":[{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301},{"id":"2311.16079","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","created":"2023-11-27","cited_by_count":274},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181},{"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":"2007.15207","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","created":"2020-07-30","cited_by_count":153},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142},{"id":"2006.06202","title":"A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages","created":"2020-06-11","cited_by_count":131},{"id":"2312.00738","title":"SeaLLMs -- Large Language Models for Southeast Asia","created":"2023-12-01","cited_by_count":104},{"id":"2402.18041","title":"Datasets for Large Language Models: A Comprehensive Survey","created":"2024-02-28","cited_by_count":71},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30},{"id":"2303.17003","title":"Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams","created":"2023-03-29","cited_by_count":25},{"id":"2305.06721","title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","created":"2023-05-11","cited_by_count":24},{"id":"1712.08917","title":"Building a Sentiment Corpus of Tweets in Brazilian Portuguese","created":"2017-12-24","cited_by_count":20},{"id":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","cited_by_count":19},{"id":"2402.18766","title":"Advancing Generative AI for Portuguese with Open Decoder Gerv\\'asio PT*","created":"2024-02-29","cited_by_count":19},{"id":"2407.18887","title":"Embedding And Clustering Your Data Can Improve Contrastive Pretraining","created":"2024-07-26","cited_by_count":17},{"id":"2402.12969","title":"Gl\\'orIA -- A Generative and Open Large Language Model for Portuguese","created":"2024-02-20","cited_by_count":16},{"id":"2307.05410","title":"BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams","created":"2023-07-11","cited_by_count":15},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13},{"id":"2403.09887","title":"Sabi\\'a-2: A New Generation of Portuguese Large Language Models","created":"2024-03-14","cited_by_count":10},{"id":"2311.01200","title":"Continual Learning Under Language Shift","created":"2023-11-02","cited_by_count":9},{"id":"2402.14652","title":"Cleaner Pretraining Corpus Curation with Neural Web Scraping","created":"2024-02-22","cited_by_count":5}],"next_cursor":null}