{"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/bias-aware-low-rank-adaptation-mitigating","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","arxiv_id":"2408.04556","date":"2024-08-08","proceeding":null,"authors":["Yupeng Chang","Yi Chang","Yuan Wu"],"abstract":"Large language models (LLMs) have demonstrated remarkable proficiency across various natural language processing (NLP) tasks. However, adapting LLMs to downstream applications requires computationally intensive and memory-demanding fine-tuning procedures. To alleviate these burdens, parameter-efficient fine-tuning (PEFT) techniques have emerged as a promising approach to tailor LLMs with minimal computational overhead. While PEFT methods offer substantial advantages, they do not fully address the pervasive issue of bias propagation from pre-training data. This work introduces Bias-Alleviating Low-Rank Adaptation (BA-LoRA), a novel PEFT method designed to counteract bias inheritance. BA-LoRA incorporates three distinct regularization terms: (1) a consistency regularizer, (2) a diversity regularizer, and (3) a singular value decomposition regularizer. These regularizers aim to enhance the models' consistency, diversity, and generalization capabilities during fine-tuning. We conduct extensive experiments on natural language understanding (NLU) and natural language generation (NLG) tasks using prominent LLMs such as LLaMA, Mistral, and Gemma. The results demonstrate that BA-LoRA outperforms LoRA and its state-of-the-art variants. Moreover, our method effectively mitigates the adverse effects of pre-training bias, leading to more reliable and robust model outputs. The code is available at https://github.com/cyp-jlu-ai/BA-LoRA.","url_abs":"https://arxiv.org/abs/2408.04556v3","url_pdf":"https://arxiv.org/pdf/2408.04556v3.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":"bias-aware-low-rank-adaptation-mitigating","repo_url":"https://github.com/cyp-jlu-ai/ba-lora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.04556","atlas_url":"https://app.syntology.ai/?focus=2408.04556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04556"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2408.04556"},"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":"2408.04556"},"call":"get_harvested_code_for_paper(arxiv_id=\"2408.04556\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2408.04556"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2408.04556\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2408.04556"},"call":"get_concepts_for_paper(arxiv_id=\"2408.04556\")"}],"by_repo":[{"repo":"cyp-jlu-ai/ba-lora","kind":"official","samples":13,"ran":12,"instrument":7,"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/2408.04556.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/2408.04556.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/cyp-jlu-ai/ba-lora","reach":{"status":"ok"}}],"summary":{"ran_violates":3,"ran_fixture":1,"ran":2,"ran_draft_wrong":6,"unverified":1},"n_samples":13,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"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":13,"ran":12,"n_ran_checked":5,"n_instrument":7,"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":13,"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":10,"n_ran_without_level_date":2,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","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":"0fe9cf6c00ef56ea","code_sha256_prefix":"0fe9cf6c00ef56ea","entry":"is_number","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/gsm8k_inference.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/gsm8k_inference.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"s:str/0/str","fixture_out_type":"bool","code_page":"/code/is-number","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"0fe9cf6c00ef56ea"}},{"code_sha256":"5c20985938875f5f","code_sha256_prefix":"5c20985938875f5f","entry":"batch_data","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/gsm8k_inference.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/gsm8k_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"data_list:list/1/Tensor, batch_size:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5c20985938875f5f"},"code_page":"/code/batch-data","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"5c20985938875f5f"}},{"code_sha256":"dccdc98b10215ab7","code_sha256_prefix":"dccdc98b10215ab7","entry":"generate_one_completion","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/humaneval.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/humaneval.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/?, sampling_params:dict/0/?, prompt:str/0/str, template:bool/0/bool","fixture_out_type":"str","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, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"dccdc98b10215ab7"}},{"code_sha256":"8ae8c583b21633b3","code_sha256_prefix":"8ae8c583b21633b3","entry":"is_digit","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/grader.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/grader.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"s:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/is-digit","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"8ae8c583b21633b3"}},{"code_sha256":"8720975b15d076e8","code_sha256_prefix":"8720975b15d076e8","entry":"last_boxed_only","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/util.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/util.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"sample:tuple/1/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":"/code/last-boxed-only","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"8720975b15d076e8"}},{"code_sha256":"0b14c648516c38a7","code_sha256_prefix":"0b14c648516c38a7","entry":"last_boxed_only_string","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/util.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"string:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"0b14c648516c38a7"},"code_page":"/code/last-boxed-only-string","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"0b14c648516c38a7"}},{"code_sha256":"5c29924486e3c3e2","code_sha256_prefix":"5c29924486e3c3e2","entry":"load_data","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"tsne_visualization.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/tsne_visualization.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":"features_dir:str/0/str, step:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/load-data","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"5c29924486e3c3e2"}},{"code_sha256":"65c738adb08e913c","code_sha256_prefix":"65c738adb08e913c","entry":"math_equal","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/grader.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/grader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prediction:str/0/str, reference:str/0/str, include_percentage:bool/0/bool, is_close:bool/0/bool, timeout:bool/0/bool","fixture_out_type":"bool","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, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"65c738adb08e913c"}},{"code_sha256":"f63c83de2a26f67c","code_sha256_prefix":"f63c83de2a26f67c","entry":"math_equal_process","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/grader.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/grader.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"param:list/1/str","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f63c83de2a26f67c"},"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, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"f63c83de2a26f67c"}},{"code_sha256":"0bbf876ced018c83","code_sha256_prefix":"0bbf876ced018c83","entry":"only_until_first_boxed_from_tokens","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/util.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/util.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"string:str/0/str, tokens:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","retrieve_with":{"tool":"get_code","code_sha256":"0bbf876ced018c83"},"code_page":"/code/only-until-first-boxed-from-tokens","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"0bbf876ced018c83"}},{"code_sha256":"48720117c27620bc","code_sha256_prefix":"48720117c27620bc","entry":"post_process","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/humaneval.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/humaneval.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"text:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","retrieve_with":{"tool":"get_code","code_sha256":"48720117c27620bc"},"code_page":"/code/post-process","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"48720117c27620bc"}},{"code_sha256":"f3bbe264b05aadd3","code_sha256_prefix":"f3bbe264b05aadd3","entry":"remove_boxed","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"inference/math_inference.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/math_inference.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"s:str/0/str","fixture_out_type":"str","retrieve_with":{"tool":"get_code","code_sha256":"f3bbe264b05aadd3"},"code_page":"/code/remove-boxed","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"f3bbe264b05aadd3"}},{"code_sha256":"1d2acce665f00dcc","code_sha256_prefix":"1d2acce665f00dcc","entry":"perform_tsne","repo":"cyp-jlu-ai/ba-lora","repo_kind":"official","path":"tsne_visualization.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/tsne_visualization.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, cyp-jlu-ai/ba-lora when it was checked","mcp_get_code":{"code_sha256":"1d2acce665f00dcc"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f3feeef3434360efc5b1268679241fb295ce875d8d3e6851a07c82e868953e35","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}