{"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/raise-a-child-in-large-language-model-towards","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","arxiv_id":"2109.05687","date":"2021-09-13","proceeding":"EMNLP 2021 11","authors":["Runxin Xu","Fuli Luo","Zhiyuan Zhang","Chuanqi Tan","Baobao Chang","Songfang Huang","Fei Huang"],"abstract":"Recent pretrained language models extend from millions to billions of parameters. Thus the need to fine-tune an extremely large pretrained model with a limited training corpus arises in various downstream tasks. In this paper, we propose a straightforward yet effective fine-tuning technique, Child-Tuning, which updates a subset of parameters (called child network) of large pretrained models via strategically masking out the gradients of the non-child network during the backward process. Experiments on various downstream tasks in GLUE benchmark show that Child-Tuning consistently outperforms the vanilla fine-tuning by 1.5~8.6 average score among four different pretrained models, and surpasses the prior fine-tuning techniques by 0.6~1.3 points. Furthermore, empirical results on domain transfer and task transfer show that Child-Tuning can obtain better generalization performance by large margins.","url_abs":"https://arxiv.org/abs/2109.05687v1","url_pdf":"https://arxiv.org/pdf/2109.05687v1.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":"raise-a-child-in-large-language-model-towards","repo_url":"https://github.com/alibaba/AliceMind","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"raise-a-child-in-large-language-model-towards","repo_url":"https://github.com/pkunlp-icler/childtuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"raise-a-child-in-large-language-model-towards","repo_url":"https://github.com/runxinxu/childtuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"child-tuning","method_name":"Child-Tuning"}],"datasets_introduced":[],"methods_introduced":[{"slug":"child-tuning","name":"Child-Tuning","full_name":"Child-Tuning"}],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2109.05687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05687"}},"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/alibaba/AliceMind","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pkunlp-icler/childtuning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/runxinxu/childtuning","reach":{"status":"ok"}}],"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":"7877ae725c2cba07","entry":"acc_and_f1","repo":"pkunlp-icler/childtuning","repo_kind":"official","path":"metric.py","file_url":"https://github.com/pkunlp-icler/childtuning/blob/HEAD/metric.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":"7877ae725c2cba07"}},{"code_sha256_prefix":"04926b8f59ec8600","entry":"pearson_and_spearman","repo":"pkunlp-icler/childtuning","repo_kind":"official","path":"metric.py","file_url":"https://github.com/pkunlp-icler/childtuning/blob/HEAD/metric.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":"04926b8f59ec8600"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":"pkunlp-icler/childtuning","repo_kind":"official","path":"metric.py","file_url":"https://github.com/pkunlp-icler/childtuning/blob/HEAD/metric.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":"3c241ecfe3749a6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}