{"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/seeking-neural-nuggets-knowledge-transfer-in","title":"Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective","arxiv_id":"2310.11451","date":"2023-10-17","proceeding":null,"authors":["Ming Zhong","Chenxin An","Weizhu Chen","Jiawei Han","Pengcheng He"],"abstract":"Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operations on these parameters to manipulate the underlying implicit knowledge (encompassing detection, editing, and merging), there remains an ambiguous understanding regarding their transferability across models with varying scales. In this paper, we seek to empirically investigate knowledge transfer from larger to smaller models through a parametric perspective. To achieve this, we employ sensitivity-based techniques to extract and align knowledge-specific parameters between different LLMs. Moreover, the LoRA module is used as the intermediary mechanism for injecting the extracted knowledge into smaller models. Evaluations across four benchmarks validate the efficacy of our proposed method. Our findings highlight the critical factors contributing to the process of parametric knowledge transfer, underscoring the transferability of model parameters across LLMs of different scales. Project website: https://maszhongming.github.io/ParaKnowTransfer.","url_abs":"https://arxiv.org/abs/2310.11451v2","url_pdf":"https://arxiv.org/pdf/2310.11451v2.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":"seeking-neural-nuggets-knowledge-transfer-in","repo_url":"https://github.com/maszhongming/paraknowtransfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.11451","atlas_url":"https://app.syntology.ai/?focus=2310.11451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11451"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maszhongming/paraknowtransfer","reach":{"status":"ok"}}],"summary":{"ran":7,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":"bb7dba115813de4b","entry":"compute_summed_area_table","repo":"maszhongming/paraknowtransfer","repo_kind":"official","path":"extract_lora_with_sensitivity.py","file_url":"https://github.com/maszhongming/paraknowtransfer/blob/HEAD/extract_lora_with_sensitivity.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb7dba115813de4b"}},{"code_sha256_prefix":"63a6761732fb4c66","entry":"format_category","repo":"maszhongming/paraknowtransfer","repo_kind":"official","path":"utils/process_mmlu.py","file_url":"https://github.com/maszhongming/paraknowtransfer/blob/HEAD/utils/process_mmlu.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63a6761732fb4c66"}},{"code_sha256_prefix":"fe46bbd2a9849bc7","entry":"get_content","repo":"maszhongming/paraknowtransfer","repo_kind":"official","path":"utils/get_sample_data.py","file_url":"https://github.com/maszhongming/paraknowtransfer/blob/HEAD/utils/get_sample_data.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":"fe46bbd2a9849bc7"}},{"code_sha256_prefix":"d342c5da9dae8b17","entry":"get_delta_lora","repo":"maszhongming/paraknowtransfer","repo_kind":"official","path":"get_delta.py","file_url":"https://github.com/maszhongming/paraknowtransfer/blob/HEAD/get_delta.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":"d342c5da9dae8b17"}},{"code_sha256_prefix":"8476123e8605e688","entry":"load_data","repo":"maszhongming/paraknowtransfer","repo_kind":"official","path":"extract_lora_with_sensitivity.py","file_url":"https://github.com/maszhongming/paraknowtransfer/blob/HEAD/extract_lora_with_sensitivity.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":"8476123e8605e688"}},{"code_sha256_prefix":"f6a7ad7946e5923d","entry":"load_jsonl","repo":"maszhongming/paraknowtransfer","repo_kind":"official","path":"utils/get_sample_data.py","file_url":"https://github.com/maszhongming/paraknowtransfer/blob/HEAD/utils/get_sample_data.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6a7ad7946e5923d"}},{"code_sha256_prefix":"c45b701667c4f10b","entry":"process","repo":"maszhongming/paraknowtransfer","repo_kind":"official","path":"utils/process_mmlu.py","file_url":"https://github.com/maszhongming/paraknowtransfer/blob/HEAD/utils/process_mmlu.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":"c45b701667c4f10b"}},{"code_sha256_prefix":"5fc5d6ac2b33e706","entry":"sum_submatrix","repo":"maszhongming/paraknowtransfer","repo_kind":"official","path":"extract_lora_with_sensitivity.py","file_url":"https://github.com/maszhongming/paraknowtransfer/blob/HEAD/extract_lora_with_sensitivity.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":"5fc5d6ac2b33e706"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}