{"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/progressive-prompts-continual-learning-for","title":"Progressive Prompts: Continual Learning for Language Models","arxiv_id":"2301.12314","date":"2023-01-29","proceeding":null,"authors":["Anastasia Razdaibiedina","Yuning Mao","Rui Hou","Madian Khabsa","Mike Lewis","Amjad Almahairi"],"abstract":"We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. Our method allows forward transfer and resists catastrophic forgetting, without relying on data replay or a large number of task-specific parameters. Progressive Prompts learns a new soft prompt for each task and sequentially concatenates it with the previously learned prompts, while keeping the base model frozen. Experiments on standard continual learning benchmarks show that our approach outperforms state-of-the-art methods, with an improvement >20% in average test accuracy over the previous best-preforming method on T5 model. We also explore a more challenging continual learning setup with longer sequences of tasks and show that Progressive Prompts significantly outperforms prior methods.","url_abs":"https://arxiv.org/abs/2301.12314v1","url_pdf":"https://arxiv.org/pdf/2301.12314v1.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":"progressive-prompts-continual-learning-for","repo_url":"https://github.com/arazd/ProgressivePrompts","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"progressive-prompts-continual-learning-for","repo_url":"https://github.com/arazd/residualprompts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"base","method_name":"BASE"},{"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"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.12314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12314"}},"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/arazd/ProgressivePrompts","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arazd/residualprompts","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"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":"8845796154a75a52","entry":"change_string","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"BERT_codebase/continual_learning_one_head.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/BERT_codebase/continual_learning_one_head.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":"8845796154a75a52"}},{"code_sha256_prefix":"39af2c05db3f2f6e","entry":"compute_class_offsets","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"BERT_codebase/continual_learning_one_head.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/BERT_codebase/continual_learning_one_head.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":"39af2c05db3f2f6e"}},{"code_sha256_prefix":"5545d5eca33677e6","entry":"get_extended_attention_mask2","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"BERT_codebase/model_utils.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/BERT_codebase/model_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":"5545d5eca33677e6"}},{"code_sha256_prefix":"a9b8784508243768","entry":"get_mask_arr","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"BERT_codebase/model_utils.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/BERT_codebase/model_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":"a9b8784508243768"}},{"code_sha256_prefix":"2e8d66e24002255e","entry":"get_permutation_batch","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"BERT_codebase/continual_learning_one_head.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/BERT_codebase/continual_learning_one_head.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":"2e8d66e24002255e"}},{"code_sha256_prefix":"78afa6f2750a1043","entry":"get_prefix_net","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"BERT_codebase/continual_learning_utils.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/BERT_codebase/continual_learning_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":"78afa6f2750a1043"}},{"code_sha256_prefix":"a59e43f3af33ac61","entry":"get_prefix_net","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"BERT_codebase/train_soft_prompt.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/BERT_codebase/train_soft_prompt.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":"a59e43f3af33ac61"}},{"code_sha256_prefix":"b8920b9ed536a3c7","entry":"train","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"T5_codebase/train_prompt.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/T5_codebase/train_prompt.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":"b8920b9ed536a3c7"}},{"code_sha256_prefix":"0c21bb10317460b6","entry":"train_prompt","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"BERT_codebase/train_soft_prompt.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/BERT_codebase/train_soft_prompt.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":"0c21bb10317460b6"}},{"code_sha256_prefix":"11448b3129bb18b8","entry":"train_step_lester","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"T5_codebase/train_prompt.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/T5_codebase/train_prompt.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":"11448b3129bb18b8"}},{"code_sha256_prefix":"f7b8ef728f606082","entry":"validate_lester","repo":"arazd/ProgressivePrompts","repo_kind":"official","path":"T5_codebase/train_prompt.py","file_url":"https://github.com/arazd/ProgressivePrompts/blob/HEAD/T5_codebase/train_prompt.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":"f7b8ef728f606082"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}