{"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/asymmetry-in-low-rank-adapters-of-foundation","title":"Asymmetry in Low-Rank Adapters of Foundation Models","arxiv_id":"2402.16842","date":"2024-02-26","proceeding":null,"authors":["Jiacheng Zhu","Kristjan Greenewald","Kimia Nadjahi","Haitz Sáez de Ocáriz Borde","Rickard Brüel Gabrielsson","Leshem Choshen","Marzyeh Ghassemi","Mikhail Yurochkin","Justin Solomon"],"abstract":"Parameter-efficient fine-tuning optimizes large, pre-trained foundation models by updating a subset of parameters; in this class, Low-Rank Adaptation (LoRA) is particularly effective. Inspired by an effort to investigate the different roles of LoRA matrices during fine-tuning, this paper characterizes and leverages unexpected asymmetry in the importance of low-rank adapter matrices. Specifically, when updating the parameter matrices of a neural network by adding a product $BA$, we observe that the $B$ and $A$ matrices have distinct functions: $A$ extracts features from the input, while $B$ uses these features to create the desired output. Based on this observation, we demonstrate that fine-tuning $B$ is inherently more effective than fine-tuning $A$, and that a random untrained $A$ should perform nearly as well as a fine-tuned one. Using an information-theoretic lens, we also bound the generalization of low-rank adapters, showing that the parameter savings of exclusively training $B$ improves the bound. We support our conclusions with experiments on RoBERTa, BART-Large, LLaMA-2, and ViTs.","url_abs":"https://arxiv.org/abs/2402.16842v2","url_pdf":"https://arxiv.org/pdf/2402.16842v2.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":"asymmetry-in-low-rank-adapters-of-foundation","repo_url":"https://github.com/Jiacheng-Zhu-AIML/AsymmetryLoRA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adapter","method_name":"Adapter"},{"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":"roberta","method_name":"RoBERTa"},{"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":"https://syntology.ai/paper/2402.16842","atlas_url":"https://app.syntology.ai/?focus=2402.16842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16842"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.16842"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.16842"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.16842\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2402.16842"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.16842\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.16842"},"call":"get_concepts_for_paper(arxiv_id=\"2402.16842\")"}],"by_repo":[{"repo":"Jiacheng-Zhu-AIML/AsymmetryLoRA","kind":"official","samples":6,"ran":5,"instrument":2,"unverified":1}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2402.16842.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2402.16842.svg"},"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/Jiacheng-Zhu-AIML/AsymmetryLoRA","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran":3,"unverified":1},"n_samples":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":6,"ran":5,"n_ran_checked":3,"n_instrument":2,"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":6,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"875f9e0e658b6c6d","code_sha256_prefix":"875f9e0e658b6c6d","entry":"STRATEGY_TO_RULE_func","repo":"Jiacheng-Zhu-AIML/AsymmetryLoRA","repo_kind":"official","path":"GPT_experiments/local_lora_configs.py","file_url":"https://github.com/Jiacheng-Zhu-AIML/AsymmetryLoRA/blob/HEAD/GPT_experiments/local_lora_configs.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"strategy_str:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jiacheng-Zhu-AIML/AsymmetryLoRA when it was checked","mcp_get_code":{"code_sha256":"875f9e0e658b6c6d"}},{"code_sha256":"96556814f1bac2ea","code_sha256_prefix":"96556814f1bac2ea","entry":"get_peft_model_state_dict_local","repo":"Jiacheng-Zhu-AIML/AsymmetryLoRA","repo_kind":"official","path":"LoRASYM_peft/local_peft_model_all.py","file_url":"https://github.com/Jiacheng-Zhu-AIML/AsymmetryLoRA/blob/HEAD/LoRASYM_peft/local_peft_model_all.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, state_dict:dict/0/?, adapter_name:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jiacheng-Zhu-AIML/AsymmetryLoRA when it was checked","mcp_get_code":{"code_sha256":"96556814f1bac2ea"}},{"code_sha256":"59f97c4aab5b76e8","code_sha256_prefix":"59f97c4aab5b76e8","entry":"match","repo":"Jiacheng-Zhu-AIML/AsymmetryLoRA","repo_kind":"official","path":"GPT_experiments/utils.py","file_url":"https://github.com/Jiacheng-Zhu-AIML/AsymmetryLoRA/blob/HEAD/GPT_experiments/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"s1:str/0/str, s2:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"59f97c4aab5b76e8"},"code_page":"/code/match","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jiacheng-Zhu-AIML/AsymmetryLoRA when it was checked","mcp_get_code":{"code_sha256":"59f97c4aab5b76e8"}},{"code_sha256":"020b699ab74fb7e1","code_sha256_prefix":"020b699ab74fb7e1","entry":"process_mcq","repo":"Jiacheng-Zhu-AIML/AsymmetryLoRA","repo_kind":"official","path":"GPT_experiments/utils.py","file_url":"https://github.com/Jiacheng-Zhu-AIML/AsymmetryLoRA/blob/HEAD/GPT_experiments/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"sample:dict/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jiacheng-Zhu-AIML/AsymmetryLoRA when it was checked","mcp_get_code":{"code_sha256":"020b699ab74fb7e1"}},{"code_sha256":"d8ca1158aeb288e1","code_sha256_prefix":"d8ca1158aeb288e1","entry":"strategy_to_rule_dict","repo":"Jiacheng-Zhu-AIML/AsymmetryLoRA","repo_kind":"official","path":"GPT_experiments/local_lora_configs.py","file_url":"https://github.com/Jiacheng-Zhu-AIML/AsymmetryLoRA/blob/HEAD/GPT_experiments/local_lora_configs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"update_A:bool/0/bool, update_B:bool/0/bool, update_E:bool/0/bool, A_init:str/0/str, B_init:str/0/str, E_init:str/0/str, use_E:bool/0/bool","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jiacheng-Zhu-AIML/AsymmetryLoRA when it was checked","mcp_get_code":{"code_sha256":"d8ca1158aeb288e1"}},{"code_sha256":"2200fea63d2ae407","code_sha256_prefix":"2200fea63d2ae407","entry":"measure_accuracy_by_category","repo":"Jiacheng-Zhu-AIML/AsymmetryLoRA","repo_kind":"official","path":"GPT_experiments/utils.py","file_url":"https://github.com/Jiacheng-Zhu-AIML/AsymmetryLoRA/blob/HEAD/GPT_experiments/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jiacheng-Zhu-AIML/AsymmetryLoRA when it was checked","mcp_get_code":{"code_sha256":"2200fea63d2ae407"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"605d2f714855193b685444ac44a1cadddaf8e48890121d9f47de58a2e579a5ed","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}