{"url":"/method/bloomz","slug":"bloomz","name":"BLOOMZ","full_name":"BLOOMZ","full_name_withheld":false,"description_markdown":"**BLOOMZ** is a Multitask prompted finetuning (MTF) variant of BLOOM.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Crosslingual Generalization through Multitask Finetuning","paper":"/paper/crosslingual-generalization-through-multitask","first_author":"Niklas Muennighoff","n_authors":19,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/crosslingual-generalization-through-multitask"},"source":{"url":"https://arxiv.org/abs/2211.01786v2","title":"Crosslingual Generalization through Multitask Finetuning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":26,"archive_num_papers":26,"papers_newest_first":[{"paper":null,"title":"Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study","date":"2025-05-09","arxiv_id":"2505.06149","n_code_links":0,"syntology":null},{"paper":null,"title":"Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks","date":"2024-05-24","arxiv_id":"2405.15453","n_code_links":0,"syntology":null},{"paper":"/paper/mozip-a-multilingual-benchmark-to-evaluate","title":"MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property","date":"2024-02-26","arxiv_id":"2402.16389","n_code_links":1,"syntology":null},{"paper":"/paper/lexc-gen-generating-data-for-extremely-low","title":"LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons","date":"2024-02-21","arxiv_id":"2402.14086","n_code_links":2,"syntology":null},{"paper":"/paper/arabicmmlu-assessing-massive-multitask","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","date":"2024-02-20","arxiv_id":"2402.12840","n_code_links":1,"syntology":{"ran":3,"of":6,"unverified":3,"pointer_only":6}},{"paper":null,"title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","date":"2024-02-12","arxiv_id":"2402.07827","n_code_links":0,"syntology":null},{"paper":null,"title":"Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon","date":"2024-02-03","arxiv_id":"2402.02113","n_code_links":0,"syntology":null},{"paper":null,"title":"Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages","date":"2024-01-11","arxiv_id":"2401.05811","n_code_links":0,"syntology":null},{"paper":null,"title":"Crosslingual Retrieval Augmented In-context Learning for Bangla","date":"2023-11-01","arxiv_id":"2311.00587","n_code_links":0,"syntology":null},{"paper":"/paper/the-skipped-beat-a-study-of-sociopragmatic","title":"The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages","date":"2023-10-23","arxiv_id":"2310.14557","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-only-pass-primary","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","date":"2023-10-07","arxiv_id":"2310.04928","n_code_links":1,"syntology":{"ran":2,"of":5,"unverified":3,"pointer_only":0}},{"paper":"/paper/flesch-or-fumble-evaluating-readability","title":"Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models","date":"2023-09-11","arxiv_id":"2309.05454","n_code_links":1,"syntology":null},{"paper":null,"title":"Efficient Finetuning Large Language Models For Vietnamese Chatbot","date":"2023-09-09","arxiv_id":"2309.04646","n_code_links":0,"syntology":null},{"paper":"/paper/translate-meanings-not-just-words-idiomkb-s","title":"Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models","date":"2023-08-26","arxiv_id":"2308.13961","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-study-of-catastrophic-forgetting","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","date":"2023-08-17","arxiv_id":"2308.08747","n_code_links":1,"syntology":null},{"paper":"/paper/ecomgpt-instruction-tuning-large-language","title":"EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce","date":"2023-08-14","arxiv_id":"2308.06966","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":1}},{"paper":"/paper/youku-mplug-a-10-million-large-scale-chinese","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","date":"2023-06-07","arxiv_id":"2306.04362","n_code_links":1,"syntology":{"ran":3,"of":13,"unverified":10,"pointer_only":0}},{"paper":null,"title":"shs-nlp at RadSum23: Domain-Adaptive Pre-training of Instruction-tuned LLMs for Radiology Report Impression Generation","date":"2023-06-05","arxiv_id":"2306.03264","n_code_links":0,"syntology":null},{"paper":null,"title":"LAraBench: Benchmarking Arabic AI with Large Language Models","date":"2023-05-24","arxiv_id":"2305.14982","n_code_links":0,"syntology":null},{"paper":"/paper/outlier-suppression-accurate-quantization-of","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","date":"2023-04-18","arxiv_id":"2304.09145","n_code_links":1,"syntology":{"ran":5,"of":7,"unverified":2,"pointer_only":0}},{"paper":"/paper/multilingual-machine-translation-with-large","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","date":"2023-04-10","arxiv_id":"2304.04675","n_code_links":2,"syntology":null},{"paper":null,"title":"Evaluating Large Language Models on a Highly-specialized Topic, Radiation Oncology Physics","date":"2023-04-01","arxiv_id":"2304.01938","n_code_links":0,"syntology":null},{"paper":null,"title":"Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages","date":"2023-03-23","arxiv_id":"2303.13592","n_code_links":0,"syntology":null},{"paper":null,"title":"Zero-Shot Cross-Lingual Summarization via Large Language Models","date":"2023-02-28","arxiv_id":"2302.14229","n_code_links":0,"syntology":null},{"paper":"/paper/bloom-1-adding-language-support-to-bloom-for","title":"BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting","date":"2022-12-19","arxiv_id":"2212.09535","n_code_links":1,"syntology":null},{"paper":"/paper/crosslingual-generalization-through-multitask","title":"Crosslingual Generalization through Multitask Finetuning","date":"2022-11-03","arxiv_id":"2211.01786","n_code_links":1,"syntology":{"ran":1,"of":4,"unverified":3,"pointer_only":0}}],"papers_shown":26,"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":6},{"task":"/task/translation","name":"Translation","papers":4},{"task":"/task/zero-shot-learning","name":"Zero-Shot Learning","papers":4},{"task":"/task/diversity","name":"Diversity","papers":3},{"task":"/task/language-modeling","name":"Language Modeling","papers":3},{"task":"/task/large-language-model","name":"Large Language Model","papers":3},{"task":"/task/machine-translation","name":"Machine Translation","papers":3},{"task":"/task/benchmarking","name":"Benchmarking","papers":2},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":2},{"task":"/task/instruction-following","name":"Instruction Following","papers":2},{"task":"/task/multi-task-language-understanding","name":"Multi-task Language Understanding","papers":2},{"task":"/task/multiple-choice","name":"Multiple-choice","papers":2},{"task":"/task/question-answering","name":"Question Answering","papers":2},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":2},{"task":"/task/zero-shot-generalization","name":"Zero-shot Generalization","papers":2},{"task":"/task/arabicmmlu","name":"ArabicMMLU","papers":1},{"task":"/task/chatbot","name":"Chatbot","papers":1},{"task":"/task/coreference-resolution","name":"Coreference Resolution","papers":1},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":1}],"tasks_shown":20,"n_tasks":41,"usage_by_year":[{"year":"2022","papers":2},{"year":"2023","papers":16},{"year":"2024","papers":7},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/bloomz"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}