{"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/understanding-domain-learning-in-language","title":"Understanding Domain Learning in Language Models Through Subpopulation Analysis","arxiv_id":"2210.12553","date":"2022-10-22","proceeding":null,"authors":["Zheng Zhao","Yftah Ziser","Shay B. Cohen"],"abstract":"We investigate how different domains are encoded in modern neural network architectures. We analyze the relationship between natural language domains, model size, and the amount of training data used. The primary analysis tool we develop is based on subpopulation analysis with Singular Vector Canonical Correlation Analysis (SVCCA), which we apply to Transformer-based language models (LMs). We compare the latent representations of such a language model at its different layers from a pair of models: a model trained on multiple domains (an experimental model) and a model trained on a single domain (a control model). Through our method, we find that increasing the model capacity impacts how domain information is stored in upper and lower layers differently. In addition, we show that larger experimental models simultaneously embed domain-specific information as if they were conjoined control models. These findings are confirmed qualitatively, demonstrating the validity of our method.","url_abs":"https://arxiv.org/abs/2210.12553v1","url_pdf":"https://arxiv.org/pdf/2210.12553v1.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":"understanding-domain-learning-in-language","repo_url":"https://github.com/zsquaredz/subpopulation_analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.12553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12553"}},"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/zsquaredz/subpopulation_analysis","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":"01472465bed8b268","entry":"compute_ccas","repo":"zsquaredz/subpopulation_analysis","repo_kind":"official","path":"code/cca_core.py","file_url":"https://github.com/zsquaredz/subpopulation_analysis/blob/HEAD/code/cca_core.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01472465bed8b268"}},{"code_sha256_prefix":"ea98389a1755bb3f","entry":"positivedef_matrix_sqrt","repo":"zsquaredz/subpopulation_analysis","repo_kind":"official","path":"code/cca_core.py","file_url":"https://github.com/zsquaredz/subpopulation_analysis/blob/HEAD/code/cca_core.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea98389a1755bb3f"}},{"code_sha256_prefix":"ffcbd13c7094948e","entry":"remove_small","repo":"zsquaredz/subpopulation_analysis","repo_kind":"official","path":"code/cca_core.py","file_url":"https://github.com/zsquaredz/subpopulation_analysis/blob/HEAD/code/cca_core.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ffcbd13c7094948e"}},{"code_sha256_prefix":"a9dd2376c565d8de","entry":"load_existing_dataset","repo":"zsquaredz/subpopulation_analysis","repo_kind":"official","path":"code/preprocess/utils.py","file_url":"https://github.com/zsquaredz/subpopulation_analysis/blob/HEAD/code/preprocess/utils.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":"a9dd2376c565d8de"}},{"code_sha256_prefix":"908a92be65ade86a","entry":"load_existing_dataset_and_create_splits","repo":"zsquaredz/subpopulation_analysis","repo_kind":"official","path":"code/preprocess/utils.py","file_url":"https://github.com/zsquaredz/subpopulation_analysis/blob/HEAD/code/preprocess/utils.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":"908a92be65ade86a"}},{"code_sha256_prefix":"41bedd34dd92f3bb","entry":"load_file","repo":"zsquaredz/subpopulation_analysis","repo_kind":"official","path":"code/preprocess/utils.py","file_url":"https://github.com/zsquaredz/subpopulation_analysis/blob/HEAD/code/preprocess/utils.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":"41bedd34dd92f3bb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}