{"url":"/method/bloom","slug":"bloom","name":"BLOOM","full_name":"BLOOM","full_name_withheld":false,"description_markdown":"**BLOOM** is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of\r\nsources in 46 natural and 13 programming languages (59 in total).","description_state":"present","introduced_year":null,"introduced_by":{"title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","paper":"/paper/bloom-a-176b-parameter-open-access","first_author":"BigScience Workshop","n_authors":394,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/bloom-a-176b-parameter-open-access"},"source":{"url":"https://arxiv.org/abs/2211.05100v4","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","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":116,"archive_num_papers":116,"papers_newest_first":[{"paper":"/paper/ai-driven-multi-source-data-fusion-for-algal","title":"AI-driven multi-source data fusion for algal bloom severity classification in small inland water bodies: Leveraging Sentinel-2, DEM, and NOAA climate data","date":"2025-05-02","arxiv_id":"2505.03808","n_code_links":1,"syntology":null},{"paper":null,"title":"Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning","date":"2025-04-08","arxiv_id":"2504.06135","n_code_links":0,"syntology":null},{"paper":null,"title":"Cascaded Learned Bloom Filter for Optimal Model-Filter Size Balance and Fast Rejection","date":"2025-02-06","arxiv_id":"2502.03696","n_code_links":0,"syntology":null},{"paper":null,"title":"How does a Multilingual LM Handle Multiple Languages?","date":"2025-02-06","arxiv_id":"2502.04269","n_code_links":0,"syntology":null},{"paper":null,"title":"Adversarially Robust Bloom Filters: Privacy, Reductions, and Open Problems","date":"2025-01-27","arxiv_id":"2501.15751","n_code_links":0,"syntology":null},{"paper":null,"title":"Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities","date":"2025-01-22","arxiv_id":"2501.12980","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-robustness-of-multilingual-llms-on","title":"Exploring Robustness of Multilingual LLMs on Real-World Noisy Data","date":"2025-01-14","arxiv_id":"2501.08322","n_code_links":1,"syntology":null},{"paper":"/paper/bloomcoreset-fast-coreset-sampling-using","title":"BloomCoreset: Fast Coreset Sampling using Bloom Filters for Fine-Grained Self-Supervised Learning","date":"2024-12-22","arxiv_id":"2412.16942","n_code_links":1,"syntology":null},{"paper":null,"title":"The Open Source Advantage in Large Language Models (LLMs)","date":"2024-12-16","arxiv_id":"2412.12004","n_code_links":0,"syntology":null},{"paper":null,"title":"Combining knowledge graphs and LLMs for hazardous chemical information management and reuse","date":"2024-12-10","arxiv_id":"2412.09644","n_code_links":0,"syntology":null},{"paper":null,"title":"Large Language Models as Mirrors of Societal Moral Standards","date":"2024-12-01","arxiv_id":"2412.00956","n_code_links":0,"syntology":null},{"paper":null,"title":"An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation","date":"2024-11-28","arxiv_id":"2411.19203","n_code_links":0,"syntology":null},{"paper":null,"title":"LA4SR: illuminating the dark proteome with generative AI","date":"2024-11-11","arxiv_id":"2411.06798","n_code_links":0,"syntology":null},{"paper":null,"title":"LSHBloom: Memory-efficient, Extreme-scale Document Deduplication","date":"2024-11-06","arxiv_id":"2411.04257","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring the Benefits of Domain-Pretraining of Generative Large Language Models for Chemistry","date":"2024-11-05","arxiv_id":"2411.03542","n_code_links":0,"syntology":null},{"paper":null,"title":"Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models","date":"2024-10-15","arxiv_id":"2410.11718","n_code_links":0,"syntology":null},{"paper":null,"title":"LSTM networks provide efficient cyanobacterial blooms forecasting even with incomplete spatio-temporal data","date":"2024-10-09","arxiv_id":"2410.08237","n_code_links":0,"syntology":null},{"paper":"/paper/commonit-commonality-aware-instruction-tuning","title":"CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions","date":"2024-10-04","arxiv_id":"2410.03077","n_code_links":1,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":2}},{"paper":null,"title":"k-mer-based approaches to bridging pangenomics and population genetics","date":"2024-09-18","arxiv_id":"2409.11683","n_code_links":0,"syntology":null},{"paper":"/paper/goldfish-monolingual-language-models-for-350","title":"Goldfish: Monolingual Language Models for 350 Languages","date":"2024-08-19","arxiv_id":"2408.10441","n_code_links":1,"syntology":{"ran":4,"of":5,"unverified":1,"pointer_only":5}},{"paper":null,"title":"Interventional Causal Structure Discovery over Graphical Models with Convergence and Optimality Guarantees","date":"2024-08-09","arxiv_id":"2408.04819","n_code_links":0,"syntology":null},{"paper":null,"title":"Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation","date":"2024-07-19","arxiv_id":"2407.14088","n_code_links":0,"syntology":null},{"paper":null,"title":"MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models","date":"2024-07-16","arxiv_id":"2407.11681","n_code_links":0,"syntology":null},{"paper":null,"title":"Language Portability Strategies for Open-domain Dialogue with Pre-trained Language Models from High to Low Resource Languages","date":"2024-07-01","arxiv_id":"2407.01315","n_code_links":0,"syntology":null},{"paper":"/paper/preference-tuning-for-toxicity-mitigation","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","date":"2024-06-23","arxiv_id":"2406.16235","n_code_links":1,"syntology":{"ran":7,"of":9,"unverified":2,"pointer_only":0}},{"paper":null,"title":"IDentity with Locality: An ideal hash for gene sequence search","date":"2024-06-21","arxiv_id":"2406.14901","n_code_links":0,"syntology":null},{"paper":null,"title":"Probing the Emergence of Cross-lingual Alignment during LLM Training","date":"2024-06-19","arxiv_id":"2406.13229","n_code_links":0,"syntology":null},{"paper":null,"title":"Estimating the Increase in Emissions caused by AI-augmented Search","date":"2024-06-17","arxiv_id":"2407.16894","n_code_links":0,"syntology":null},{"paper":null,"title":"Multilingual Large Language Models and Curse of Multilinguality","date":"2024-06-15","arxiv_id":"2406.10602","n_code_links":0,"syntology":null},{"paper":null,"title":"LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback","date":"2024-06-03","arxiv_id":"2406.01771","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":17},{"task":"/task/language-modeling","name":"Language Modeling","papers":12},{"task":"/task/machine-translation","name":"Machine Translation","papers":8},{"task":"/task/question-answering","name":"Question Answering","papers":8},{"task":"/task/text-generation","name":"Text Generation","papers":8},{"task":"/task/large-language-model","name":"Large Language Model","papers":6},{"task":"/task/translation","name":"Translation","papers":6},{"task":"/task/quantization","name":"Quantization","papers":5},{"task":"/task/model","name":"model","papers":5},{"task":"/task/benchmarking","name":"Benchmarking","papers":4},{"task":"/task/decoder","name":"Decoder","papers":4},{"task":"/task/retrieval","name":"Retrieval","papers":4},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":3},{"task":"/task/diversity","name":"Diversity","papers":3},{"task":null,"name":"GPU","papers":3},{"task":"/task/instruction-following","name":"Instruction Following","papers":3},{"task":"/task/mmlu","name":"MMLU","papers":3},{"task":"/task/math","name":"Math","papers":3},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":3},{"task":"/task/sentence","name":"Sentence","papers":3}],"tasks_shown":20,"n_tasks":140,"usage_by_year":[{"year":"2022","papers":11},{"year":"2023","papers":53},{"year":"2024","papers":45},{"year":"2025","papers":7}],"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/bloom"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}