{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ext5-towards-extreme-multi-task-scaling-for-1","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","arxiv_id":"2111.10952","date":"2021-11-22","proceeding":"ICLR 2022 4","authors":["Vamsi Aribandi","Yi Tay","Tal Schuster","Jinfeng Rao","Huaixiu Steven Zheng","Sanket Vaibhav Mehta","Honglei Zhuang","Vinh Q. Tran","Dara Bahri","Jianmo Ni","Jai Gupta","Kai Hui","Sebastian Ruder","Donald Metzler"],"abstract":"Despite the recent success of multi-task learning and transfer learning for natural language processing (NLP), few works have systematically studied the effect of scaling up the number of tasks during pre-training. Towards this goal, this paper introduces ExMix (Extreme Mixture): a massive collection of 107 supervised NLP tasks across diverse domains and task-families. Using ExMix, we study the effect of multi-task pre-training at the largest scale to date, and analyze co-training transfer amongst common families of tasks. Through this analysis, we show that manually curating an ideal set of tasks for multi-task pre-training is not straightforward, and that multi-task scaling can vastly improve models on its own. Finally, we propose ExT5: a model pre-trained using a multi-task objective of self-supervised span denoising and supervised ExMix. Via extensive experiments, we show that ExT5 outperforms strong T5 baselines on SuperGLUE, GEM, Rainbow, Closed-Book QA tasks, and several tasks outside of ExMix. ExT5 also significantly improves sample efficiency while pre-training.","url_abs":"https://arxiv.org/abs/2111.10952v2","url_pdf":"https://arxiv.org/pdf/2111.10952v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ext5-towards-extreme-multi-task-scaling-for-1","repo_url":"https://github.com/google-research/text-to-text-transfer-transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ext5-towards-extreme-multi-task-scaling-for-1","repo_url":"https://github.com/tensorflow/mesh","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"ext5-towards-extreme-multi-task-scaling-for-1","repo_url":"https://github.com/Mind23-2/MindCode-148","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"ext5-towards-extreme-multi-task-scaling-for-1","repo_url":"https://github.com/MindCode-4/code-5/tree/main/t5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.10952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.10952"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-5/tree/main/t5","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-148","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/mesh","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/text-to-text-transfer-transformer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ea645f2c33765137","entry":"filter_features","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/models/utils.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea645f2c33765137"}},{"code_sha256_prefix":"f9701b35213138f0","entry":"get_eval_metric_values","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/evaluation/eval_utils.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/evaluation/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9701b35213138f0"}},{"code_sha256_prefix":"a4895b42cf3f388d","entry":"get_step_from_checkpoint_path","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/models/utils.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4895b42cf3f388d"}},{"code_sha256_prefix":"62dbc58154aa737e","entry":"normalize_squad","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/evaluation/qa_utils.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/evaluation/qa_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"62dbc58154aa737e"}},{"code_sha256_prefix":"748cf9475c59f2c2","entry":"normalize_trivia_qa","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/evaluation/qa_utils.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/evaluation/qa_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"748cf9475c59f2c2"}},{"code_sha256_prefix":"4c75d412b9154a9d","entry":"qa_metrics","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/evaluation/qa_utils.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/evaluation/qa_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c75d412b9154a9d"}},{"code_sha256_prefix":"46c76c8dc7bbf945","entry":"rouge","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/evaluation/metrics.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/evaluation/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"46c76c8dc7bbf945"}},{"code_sha256_prefix":"2274158e8735347f","entry":"rouge_mean","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/evaluation/metrics.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/evaluation/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2274158e8735347f"}},{"code_sha256_prefix":"c4b3db3eab3b63b8","entry":"sort_columns","repo":"google-research/text-to-text-transfer-transformer","repo_kind":"official","path":"t5/evaluation/eval_utils.py","file_url":"https://github.com/google-research/text-to-text-transfer-transformer/blob/HEAD/t5/evaluation/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c4b3db3eab3b63b8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}