{"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/propulsion-steering-llm-with-tiny-fine-tuning","title":"Propulsion: Steering LLM with Tiny Fine-Tuning","arxiv_id":"2409.10927","date":"2024-09-17","proceeding":null,"authors":["Md Kowsher","Nusrat Jahan Prottasha","Prakash Bhat"],"abstract":"The rapid advancements in Large Language Models (LLMs) have revolutionized natural language processing (NLP) and related fields. However, fine-tuning these models for specific tasks remains computationally expensive and risks degrading pre-learned features. To address these challenges, we propose Propulsion, a novel parameter efficient fine-tuning (PEFT) method designed to optimize task-specific performance while drastically reducing computational overhead. Inspired by the concept of controlled adjustments in physical motion, Propulsion selectively re-scales specific dimensions of a pre-trained model, guiding output predictions toward task objectives without modifying the model's parameters. By introducing lightweight, trainable Propulsion parameters at the pre-trained layer, we minimize the number of parameters updated during fine-tuning, preventing overfitting or overwriting of existing knowledge. Our theoretical analysis, supported by Neural Tangent Kernel (NTK) theory, shows that Propulsion approximates the performance of full fine-tuning with far fewer trainable parameters. Empirically, Propulsion reduces the parameter count from 355.3 million to just 0.086 million, achieving over a 10x reduction compared to standard approaches like LoRA while maintaining competitive performance across benchmarks.","url_abs":"https://arxiv.org/abs/2409.10927v3","url_pdf":"https://arxiv.org/pdf/2409.10927v3.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":"propulsion-steering-llm-with-tiny-fine-tuning","repo_url":"https://github.com/Kowsher/Propulsion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.10927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.10927"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kowsher/Propulsion","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"44ee71ec7cb0bca2","entry":"build_relative_position","repo":"Kowsher/Propulsion","repo_kind":"official","path":"Src/LM/deberta.py","file_url":"https://github.com/Kowsher/Propulsion/blob/HEAD/Src/LM/deberta.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":"44ee71ec7cb0bca2"}},{"code_sha256_prefix":"38f46ef4e03fee1c","entry":"create_position_ids_from_input_ids","repo":"Kowsher/Propulsion","repo_kind":"official","path":"Src/LM/roberta.py","file_url":"https://github.com/Kowsher/Propulsion/blob/HEAD/Src/LM/roberta.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":"38f46ef4e03fee1c"}},{"code_sha256_prefix":"cde5a0a5f4074d68","entry":"make_log_bucket_position","repo":"Kowsher/Propulsion","repo_kind":"official","path":"Src/LM/deberta.py","file_url":"https://github.com/Kowsher/Propulsion/blob/HEAD/Src/LM/deberta.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":"cde5a0a5f4074d68"}},{"code_sha256_prefix":"11c7e96cb235d1f7","entry":"get_mask","repo":"Kowsher/Propulsion","repo_kind":"official","path":"Src/LM/deberta.py","file_url":"https://github.com/Kowsher/Propulsion/blob/HEAD/Src/LM/deberta.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":"11c7e96cb235d1f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}