{"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/diablo-diagonal-blocks-are-sufficient-for","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","arxiv_id":"2506.03230","date":"2025-06-03","proceeding":null,"authors":["Selcuk Gurses","Aozhong zhang","Yanxia Deng","Xun Dong","Xin Li","Naigang Wang","Penghang Yin","Zi Yang"],"abstract":"Finetuning is a critical step for adapting large language models (LLMs) to domain-specific downstream tasks. To mitigate the substantial computational and memory costs of full-model fine-tuning, Parameter-Efficient Finetuning (PEFT) methods have been proposed to update only a small subset of model parameters. However, performance gaps between PEFT approaches and full-model fine-tuning still exist. In this work, we present DiaBlo, a simple yet effective PEFT approach that updates only the diagonal blocks of selected model weight matrices. Unlike Low Rank Adaptation (LoRA) and its variants, DiaBlo eliminates the need for low rank matrix products, thereby avoiding the reliance on auxiliary initialization schemes or customized optimization strategies to improve convergence. This design leads to stable and robust convergence while maintaining comparable memory efficiency and training speed to LoRA. We conduct extensive experiments across a range of tasks, including commonsense reasoning, arithmetic reasoning, code generation, and safety alignment, to evaluate the effectiveness and efficiency of DiaBlo. Across these benchmarks, DiaBlo demonstrates strong and consistent performance while maintaining high memory efficiency and fast finetuning speed. Codes are available at https://github.com/ziyangjoy/DiaBlo.","url_abs":"https://arxiv.org/abs/2506.03230v1","url_pdf":"https://arxiv.org/pdf/2506.03230v1.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":"diablo-diagonal-blocks-are-sufficient-for","repo_url":"https://github.com/ziyangjoy/diablo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"safety-alignment","task_name":"Safety Alignment"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2506.03230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.03230"}},"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/ziyangjoy/DiaBlo","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ziyangjoy/diablo","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":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":3,"samples":[{"code_sha256_prefix":"6923df4a400a5cd9","entry":"BlockLinear","repo":"ziyangjoy/diablo","repo_kind":"official","path":"diablo/block_linear.py","file_url":"https://github.com/ziyangjoy/diablo/blob/HEAD/diablo/block_linear.py","link_basis":"first_harvest_node","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":"6923df4a400a5cd9"}},{"code_sha256_prefix":"03a0c4249091f289","entry":"generate_prompt","repo":"ziyangjoy/diablo","repo_kind":"official","path":"evaluate_commonsense.py","file_url":"https://github.com/ziyangjoy/diablo/blob/HEAD/evaluate_commonsense.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"03a0c4249091f289"}},{"code_sha256_prefix":"95f77b72bcc7ef90","entry":"extract_answer","repo":"ziyangjoy/diablo","repo_kind":"official","path":"evaluate_commonsense.py","file_url":"https://github.com/ziyangjoy/diablo/blob/HEAD/evaluate_commonsense.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":"95f77b72bcc7ef90"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}