{"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/denselora-dense-low-rank-adaptation-of-large","title":"DenseLoRA: Dense Low-Rank Adaptation of Large Language Models","arxiv_id":"2505.23808","date":"2025-05-27","proceeding":null,"authors":["Lin Mu","Xiaoyu Wang","Li Ni","Yang Li","Zhize Wu","Peiquan Jin","Yiwen Zhang"],"abstract":"Low-rank adaptation (LoRA) has been developed as an efficient approach for adapting large language models (LLMs) by fine-tuning two low-rank matrices, thereby reducing the number of trainable parameters. However, prior research indicates that many of the weights in these matrices are redundant, leading to inefficiencies in parameter utilization. To address this limitation, we introduce Dense Low-Rank Adaptation (DenseLoRA), a novel approach that enhances parameter efficiency while achieving superior performance compared to LoRA. DenseLoRA builds upon the concept of representation fine-tuning, incorporating a single Encoder-Decoder to refine and compress hidden representations across all adaptation layers before applying adaptation. Instead of relying on two redundant low-rank matrices as in LoRA, DenseLoRA adapts LLMs through a dense low-rank matrix, improving parameter utilization and adaptation efficiency. We evaluate DenseLoRA on various benchmarks, showing that it achieves 83.8% accuracy with only 0.01% of trainable parameters, compared to LoRA's 80.8% accuracy with 0.70% of trainable parameters on LLaMA3-8B. Additionally, we conduct extensive experiments to systematically assess the impact of DenseLoRA's components on overall model performance. Code is available at https://github.com/mulin-ahu/DenseLoRA.","url_abs":"https://arxiv.org/abs/2505.23808v1","url_pdf":"https://arxiv.org/pdf/2505.23808v1.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":"denselora-dense-low-rank-adaptation-of-large","repo_url":"https://github.com/mulin-ahu/denselora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.23808","atlas_url":"https://app.syntology.ai/?focus=2505.23808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23808"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/mulin-ahu/DenseLoRA","reach":null}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"d82bb63b6ee3c783","entry":"is_bnb_available","repo":"mulin-ahu/DenseLoRA","repo_kind":"official","path":"commonsense_reasoning/peft/src/peft/tuners/dora.py","file_url":"https://github.com/mulin-ahu/DenseLoRA/blob/HEAD/commonsense_reasoning/peft/src/peft/tuners/dora.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d82bb63b6ee3c783"}},{"code_sha256_prefix":"a58e8cf6e1c2220e","entry":"DoraModel","repo":"mulin-ahu/DenseLoRA","repo_kind":"official","path":"commonsense_reasoning/peft/src/peft/tuners/dora.py","file_url":"https://github.com/mulin-ahu/DenseLoRA/blob/HEAD/commonsense_reasoning/peft/src/peft/tuners/dora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a58e8cf6e1c2220e"}},{"code_sha256_prefix":"046f66c06c69cf03","entry":"Linear","repo":"mulin-ahu/DenseLoRA","repo_kind":"official","path":"commonsense_reasoning/peft/src/peft/tuners/dora.py","file_url":"https://github.com/mulin-ahu/DenseLoRA/blob/HEAD/commonsense_reasoning/peft/src/peft/tuners/dora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"046f66c06c69cf03"}},{"code_sha256_prefix":"62fbfee1f7ede251","entry":"mark_only_lora_as_trainable","repo":"mulin-ahu/DenseLoRA","repo_kind":"official","path":"commonsense_reasoning/peft/src/peft/tuners/dora.py","file_url":"https://github.com/mulin-ahu/DenseLoRA/blob/HEAD/commonsense_reasoning/peft/src/peft/tuners/dora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"62fbfee1f7ede251"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}