{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/continual-learning-of-language-models","title":"Continual Pre-training of Language Models","arxiv_id":"2302.03241","date":"2023-02-07","proceeding":null,"authors":["Zixuan Ke","Yijia Shao","Haowei Lin","Tatsuya Konishi","Gyuhak Kim","Bing Liu"],"abstract":"Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain-adaptive pre-training (or continual DAP-training). Existing research has shown that further pre-training an LM using a domain corpus to adapt the LM to the domain can improve the end-task performance in the domain. This paper proposes a novel method to continually DAP-train an LM with a sequence of unlabeled domain corpora to adapt the LM to these domains to improve their end-task performances. The key novelty of our method is a soft-masking mechanism that directly controls the update to the LM. A novel proxy is also proposed to preserve the general knowledge in the original LM. Additionally, it contrasts the representations of the previously learned domain knowledge (including the general knowledge in the pre-trained LM) and the knowledge from the current full network to achieve knowledge integration. The method not only overcomes catastrophic forgetting, but also achieves knowledge transfer to improve end-task performances. Empirical evaluation demonstrates the effectiveness of the proposed method.","url_abs":"https://arxiv.org/abs/2302.03241v4","url_pdf":"https://arxiv.org/pdf/2302.03241v4.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-learning-of-language-models","repo_url":"https://github.com/UIC-Liu-Lab/ContinualLM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continual-learning-of-language-models","repo_url":"https://github.com/zixuanke/pycontinual","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"continual-pretraining","task_name":"Continual Pretraining"},{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-pretraining-on-acl-arc","task":"Continual Pretraining","dataset":"ACL-ARC","model":"DAS","rank_in_archive_order":1,"of":1,"metrics":{"F1 (macro)":"0.6936"},"uses_additional_data":false},{"leaderboard":"/sota/continual-pretraining-on-scierc","task":"Continual Pretraining","dataset":"SciERC","model":"DAS","rank_in_archive_order":1,"of":1,"metrics":{"F1 (macro)":"0.7093"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.03241","atlas_url":"https://app.syntology.ai/?focus=2302.03241","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2302.03241"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2302.03241\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2302.03241"},"call":"get_concepts_for_paper(arxiv_id=\"2302.03241\")"}],"by_repo":[{"repo":"UIC-Liu-Lab/ContinualLM","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zixuanke/pycontinual","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"178774f134f16c4a967c2e2ff5267a11a9d7d60a35028342789dd268596b315c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}