{"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/a-closer-look-at-how-fine-tuning-changes-bert","title":"A Closer Look at How Fine-tuning Changes BERT","arxiv_id":"2106.14282","date":"2021-06-27","proceeding":"ACL 2022 5","authors":["Yichu Zhou","Vivek Srikumar"],"abstract":"Given the prevalence of pre-trained contextualized representations in today's NLP, there have been many efforts to understand what information they contain, and why they seem to be universally successful. The most common approach to use these representations involves fine-tuning them for an end task. Yet, how fine-tuning changes the underlying embedding space is less studied. In this work, we study the English BERT family and use two probing techniques to analyze how fine-tuning changes the space. We hypothesize that fine-tuning affects classification performance by increasing the distances between examples associated with different labels. We confirm this hypothesis with carefully designed experiments on five different NLP tasks. Via these experiments, we also discover an exception to the prevailing wisdom that \"fine-tuning always improves performance\". Finally, by comparing the representations before and after fine-tuning, we discover that fine-tuning does not introduce arbitrary changes to representations; instead, it adjusts the representations to downstream tasks while largely preserving the original spatial structure of the data points.","url_abs":"https://arxiv.org/abs/2106.14282v3","url_pdf":"https://arxiv.org/pdf/2106.14282v3.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":"a-closer-look-at-how-fine-tuning-changes-bert","repo_url":"https://github.com/utahnlp/BERT-fine-tuning-analysis","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.14282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14282"}},"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/utahnlp/BERT-fine-tuning-analysis","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":"bf4b967c85115c8b","entry":"load_embeddings","repo":"utahnlp/BERT-fine-tuning-analysis","repo_kind":"official","path":"probing/utils.py","file_url":"https://github.com/utahnlp/BERT-fine-tuning-analysis/blob/HEAD/probing/utils.py","link_basis":"first_harvest_node","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":"bf4b967c85115c8b"}},{"code_sha256_prefix":"90b053029f12c7a5","entry":"load_entities","repo":"utahnlp/BERT-fine-tuning-analysis","repo_kind":"official","path":"probing/utils.py","file_url":"https://github.com/utahnlp/BERT-fine-tuning-analysis/blob/HEAD/probing/utils.py","link_basis":"first_harvest_node","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":"90b053029f12c7a5"}},{"code_sha256_prefix":"2d7199caf1f33be2","entry":"load_labels","repo":"utahnlp/BERT-fine-tuning-analysis","repo_kind":"official","path":"probing/utils.py","file_url":"https://github.com/utahnlp/BERT-fine-tuning-analysis/blob/HEAD/probing/utils.py","link_basis":"first_harvest_node","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":"2d7199caf1f33be2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}