{"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/kasa-knowledge-aware-singular-value","title":"KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models","arxiv_id":"2412.06071","date":"2024-12-08","proceeding":null,"authors":["Fan Wang","Juyong Jiang","Chansung Park","Sunghun Kim","Jing Tang"],"abstract":"The increasing sizes of large language models (LLMs) result in significant computational overhead and memory usage when adapting these models to specific tasks or domains. Various parameter-efficient fine-tuning (PEFT) methods have been devised to mitigate these challenges by training a small set of parameters for the task-specific updates of the model weights. Among PEFT methods, LoRA stands out for its simplicity and efficiency, inspiring the development of a series of variants. However, LoRA and its successors disregard the knowledge that is noisy or irrelevant to the targeted task, detrimentally impacting model performance and leading to suboptimality. To address this limitation, we introduce Knowledge-aware Singular-value Adaptation (KaSA), a PEFT method that leverages singular value decomposition (SVD) with knowledge-aware singular values to dynamically activate knowledge based on its relevance to the task at hand. We conduct extensive experiments across a range of LLMs on tasks spanning natural language understanding (NLU), generation (NLG), instruction following, and commonsense reasoning. The experimental results demonstrate that KaSA consistently outperforms FFT and 14 popular PEFT baselines across 16 benchmarks and 4 synthetic datasets, underscoring our method's efficacy and adaptability. The source code of our method is available at https://github.com/juyongjiang/KaSA.","url_abs":"https://arxiv.org/abs/2412.06071v1","url_pdf":"https://arxiv.org/pdf/2412.06071v1.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":"kasa-knowledge-aware-singular-value","repo_url":"https://github.com/juyongjiang/kasa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.06071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06071"}},"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":"deterministic:regex_extraction","url":"https://github.com/juyongjiang/KaSA","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/juyongjiang/kasa","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"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":8,"samples":[{"code_sha256_prefix":"ecf94b05123201e3","entry":"bloom_model_postprocess_past_key_value","repo":"juyongjiang/KaSA","repo_kind":"official","path":"peft/src/peft/utils/constants.py","file_url":"https://github.com/juyongjiang/KaSA/blob/HEAD/peft/src/peft/utils/constants.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecf94b05123201e3"}},{"code_sha256_prefix":"6bd3015fbb224583","entry":"BaseTunerLayer","repo":"juyongjiang/kasa","repo_kind":"official","path":"peft/src/peft/tuners/vera/layer.py","file_url":"https://github.com/juyongjiang/kasa/blob/HEAD/peft/src/peft/tuners/vera/layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6bd3015fbb224583"}},{"code_sha256_prefix":"0b21aa2f3160d34c","entry":"VeraLayer","repo":"juyongjiang/kasa","repo_kind":"official","path":"peft/src/peft/tuners/vera/layer.py","file_url":"https://github.com/juyongjiang/kasa/blob/HEAD/peft/src/peft/tuners/vera/layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b21aa2f3160d34c"}},{"code_sha256_prefix":"a99ac087e4787f7c","entry":"check_adapters_to_merge","repo":"juyongjiang/KaSA","repo_kind":"official","path":"peft/src/peft/tuners/tuners_utils.py","file_url":"https://github.com/juyongjiang/KaSA/blob/HEAD/peft/src/peft/tuners/tuners_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a99ac087e4787f7c"}},{"code_sha256_prefix":"6a1220317ec3675f","entry":"check_if_peft_model","repo":"juyongjiang/KaSA","repo_kind":"official","path":"peft/src/peft/helpers.py","file_url":"https://github.com/juyongjiang/KaSA/blob/HEAD/peft/src/peft/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a1220317ec3675f"}},{"code_sha256_prefix":"c49fdcabd715ffef","entry":"check_target_module_exists","repo":"juyongjiang/KaSA","repo_kind":"official","path":"peft/src/peft/tuners/tuners_utils.py","file_url":"https://github.com/juyongjiang/KaSA/blob/HEAD/peft/src/peft/tuners/tuners_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c49fdcabd715ffef"}},{"code_sha256_prefix":"a3daaf3e5bdfc709","entry":"is_torch_tpu_available","repo":"juyongjiang/KaSA","repo_kind":"official","path":"peft/src/peft/import_utils.py","file_url":"https://github.com/juyongjiang/KaSA/blob/HEAD/peft/src/peft/import_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a3daaf3e5bdfc709"}},{"code_sha256_prefix":"249c10407ed14893","entry":"starcoder_model_postprocess_past_key_value","repo":"juyongjiang/KaSA","repo_kind":"official","path":"peft/src/peft/utils/constants.py","file_url":"https://github.com/juyongjiang/KaSA/blob/HEAD/peft/src/peft/utils/constants.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"249c10407ed14893"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}