{"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/continual-t0-progressively-instructing-50","title":"Fine-tuned Language Models are Continual Learners","arxiv_id":"2205.12393","date":"2022-05-24","proceeding":null,"authors":["Thomas Scialom","Tuhin Chakrabarty","Smaranda Muresan"],"abstract":"Recent work on large language models relies on the intuition that most natural language processing tasks can be described via natural language instructions. Language models trained on these instructions show strong zero-shot performance on several standard datasets. However, these models even though impressive still perform poorly on a wide range of tasks outside of their respective training and evaluation sets. To address this limitation, we argue that a model should be able to keep extending its knowledge and abilities, without forgetting previous skills. In spite of the limited success of Continual Learning we show that Language Models can be continual learners. We empirically investigate the reason for this success and conclude that Continual Learning emerges from self-supervision pre-training. Our resulting model Continual-T0 (CT0) is able to learn diverse new tasks, while still maintaining good performance on previous tasks, spanning remarkably through 70 datasets in total. Finally, we show that CT0 is able to combine instructions in ways it was never trained for, demonstrating some compositionality.","url_abs":"https://arxiv.org/abs/2205.12393v4","url_pdf":"https://arxiv.org/pdf/2205.12393v4.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":"continual-t0-progressively-instructing-50","repo_url":"https://github.com/thomasscialom/t0_continual_learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.12393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12393"}},"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/thomasscialom/t0_continual_learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"d7b07b7354272c69","entry":"getConstrainResults","repo":"thomasscialom/t0_continual_learning","repo_kind":"official","path":"t0_continual_learning/paper_discussion.py","file_url":"https://github.com/thomasscialom/t0_continual_learning/blob/HEAD/t0_continual_learning/paper_discussion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7b07b7354272c69"}},{"code_sha256_prefix":"1beb2af759f5b17f","entry":"getHaikuEmotionResults","repo":"thomasscialom/t0_continual_learning","repo_kind":"official","path":"t0_continual_learning/paper_discussion.py","file_url":"https://github.com/thomasscialom/t0_continual_learning/blob/HEAD/t0_continual_learning/paper_discussion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1beb2af759f5b17f"}},{"code_sha256_prefix":"d6bcda24755aa338","entry":"printDf","repo":"thomasscialom/t0_continual_learning","repo_kind":"official","path":"t0_continual_learning/paper_discussion.py","file_url":"https://github.com/thomasscialom/t0_continual_learning/blob/HEAD/t0_continual_learning/paper_discussion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6bcda24755aa338"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}