{"url":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","slug":"parameter-efficient-fine-tuning","description_markdown":"Parameter-Efficient Fine-Tuning (PEFT) is a technique used to adapt pre-trained models to new tasks with minimal changes to the model's parameters. This approach is particularly useful in scenarios where computational resources are limited or when it is desirable to maintain the original model's performance on the initial task.","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":935,"papers_with_code":441,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-boolq","slug":"parameter-efficient-fine-tuning-on-boolq","dataset":"BoolQ","dataset_url":"/dataset/boolq","rows_in_archive":4,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"LLaMA2-7b","paper_title":"QLoRA: Efficient Finetuning of Quantized LLMs","paper_url":"/paper/qlora-efficient-finetuning-of-quantized-llms","paper_date":"2023-05-23","arxiv_id":"2305.14314","code_links":[{"title":"qwenlm/qwen","url":"https://github.com/qwenlm/qwen"},{"title":"QwenLM/Qwen-7B","url":"https://github.com/QwenLM/Qwen-7B"},{"title":"artidoro/qlora","url":"https://github.com/artidoro/qlora"},{"title":"huggingface/text-generation-inference","url":"https://github.com/huggingface/text-generation-inference"},{"title":"timdettmers/bitsandbytes","url":"https://github.com/timdettmers/bitsandbytes"},{"title":"qwenlm/qwen-vl","url":"https://github.com/qwenlm/qwen-vl"},{"title":"internlm/xtuner","url":"https://github.com/internlm/xtuner"},{"title":"openmedlab/pulse","url":"https://github.com/openmedlab/pulse"},{"title":"flagai-open/aquila2","url":"https://github.com/flagai-open/aquila2"},{"title":"pilancilab/caldera","url":"https://github.com/pilancilab/caldera"},{"title":"daniel-furman/sft-demos","url":"https://github.com/daniel-furman/sft-demos"},{"title":"ist-daslab/rosa","url":"https://github.com/ist-daslab/rosa"},{"title":"cornell-zhang/llm-datatypes","url":"https://github.com/cornell-zhang/llm-datatypes"},{"title":"brandon3964/multimodal-task-vector","url":"https://github.com/brandon3964/multimodal-task-vector"},{"title":"BatsResearch/LexC-Gen","url":"https://github.com/BatsResearch/LexC-Gen"},{"title":"jerrywu-code/susgen","url":"https://github.com/jerrywu-code/susgen"},{"title":"12kimih/hicupid","url":"https://github.com/12kimih/hicupid"},{"title":"Luohh5/Chain-of-Exemplar","url":"https://github.com/Luohh5/Chain-of-Exemplar"},{"title":"erikaawang/probing-multilingual-dynamics","url":"https://github.com/erikaawang/probing-multilingual-dynamics"},{"title":"Rain9876/ShareLoRA","url":"https://github.com/Rain9876/ShareLoRA"}],"syntology":{"n":26,"n_ran":17,"n_unverified":9,"n_pointer_only":17}}},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-hellaswag","slug":"parameter-efficient-fine-tuning-on-hellaswag","dataset":"HellaSwag","dataset_url":"/dataset/hellaswag","rows_in_archive":3,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"LLaMA2-7b","paper_title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","paper_url":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","paper_date":"2024-08-27","arxiv_id":"2408.15300","code_links":[{"title":"On-Point-RND/GIFT_SW","url":"https://github.com/On-Point-RND/GIFT_SW"}],"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":3}}},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-winogrande","slug":"parameter-efficient-fine-tuning-on-winogrande","dataset":"WinoGrande","dataset_url":"/dataset/winogrande","rows_in_archive":3,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"LLaMA2-7b","paper_title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","paper_url":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","paper_date":"2024-08-27","arxiv_id":"2408.15300","code_links":[{"title":"On-Point-RND/GIFT_SW","url":"https://github.com/On-Point-RND/GIFT_SW"}],"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":3}}}],"datasets":[{"url":"/dataset/hellaswag","name":"HellaSwag","full_name":"","num_papers_in_archive":994},{"url":"/dataset/winogrande","name":"WinoGrande","full_name":"","num_papers_in_archive":703},{"url":"/dataset/boolq","name":"BoolQ","full_name":"Boolean Questions","num_papers_in_archive":701}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":441,"tagged_in_all":935,"items":[{"url":"/paper/lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","repositories_listed":74,"syntology":{"n":84,"n_ran":34,"n_unverified":50,"n_pointer_only":28}},{"url":"/paper/qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","repositories_listed":20,"syntology":{"n":26,"n_ran":17,"n_unverified":9,"n_pointer_only":17}},{"url":"/paper/any2point-empowering-any-modality-large","title":"Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding","date":"2024-04-11","arxiv_id":"2404.07989","repositories_listed":7,"syntology":{"n":24,"n_ran":15,"n_unverified":9,"n_pointer_only":24}},{"url":"/paper/point-peft-parameter-efficient-fine-tuning","title":"Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models","date":"2023-10-04","arxiv_id":"2310.03059","repositories_listed":7,"syntology":null},{"url":"/paper/bitfit-simple-parameter-efficient-fine-tuning","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","date":"2021-06-18","arxiv_id":"2106.10199","repositories_listed":6,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/dora-weight-decomposed-low-rank-adaptation","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","date":"2024-02-14","arxiv_id":"2402.09353","repositories_listed":5,"syntology":{"n":15,"n_ran":8,"n_unverified":7,"n_pointer_only":14}},{"url":"/paper/point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","arxiv_id":"2309.00615","repositories_listed":5,"syntology":{"n":20,"n_ran":13,"n_unverified":7,"n_pointer_only":7}},{"url":"/paper/dora-enhancing-parameter-efficient-fine","title":"DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution","date":"2024-05-27","arxiv_id":"2405.17357","repositories_listed":4,"syntology":null},{"url":"/paper/s-lora-serving-thousands-of-concurrent-lora","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","date":"2023-11-06","arxiv_id":"2311.03285","repositories_listed":4,"syntology":null},{"url":"/paper/longlora-efficient-fine-tuning-of-long","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","date":"2023-09-21","arxiv_id":"2309.12307","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/bone-block-affine-transformation-as-parameter","title":"Balancing LoRA Performance and Efficiency with Simple Shard Sharing","date":"2024-09-19","arxiv_id":"2409.15371","repositories_listed":3,"syntology":null},{"url":"/paper/segment-any-text-a-universal-approach-for","title":"Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation","date":"2024-06-24","arxiv_id":"2406.16678","repositories_listed":3,"syntology":null},{"url":"/paper/analyzing-the-impact-of-data-selection-and","title":"PoliTune: Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in Large Language Models","date":"2024-04-10","arxiv_id":"2404.08699","repositories_listed":3,"syntology":null},{"url":"/paper/an-embarrassingly-simple-approach-for-llm","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","date":"2024-02-13","arxiv_id":"2402.08846","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-route-among-specialized-experts","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","date":"2024-02-08","arxiv_id":"2402.05859","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/moelora-an-moe-based-parameter-efficient-fine","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","date":"2023-10-21","arxiv_id":"2310.18339","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/owq-lessons-learned-from-activation-outliers","title":"OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models","date":"2023-06-04","arxiv_id":"2306.02272","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/glyphdraw-learning-to-draw-chinese-characters","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","date":"2023-03-31","arxiv_id":"2303.17870","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/taste-text-aligned-speech-tokenization-and","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","date":"2025-04-09","arxiv_id":"2504.07053","repositories_listed":2,"syntology":{"n":20,"n_ran":14,"n_unverified":6,"n_pointer_only":20}},{"url":"/paper/farexstance-explainable-stance-detection-for","title":"FarExStance: Explainable Stance Detection for Farsi","date":"2024-12-18","arxiv_id":"2412.14008","repositories_listed":2,"syntology":null},{"url":"/paper/prompt-compression-for-large-language-models","title":"Prompt Compression for Large Language Models: A Survey","date":"2024-10-16","arxiv_id":"2410.12388","repositories_listed":2,"syntology":null},{"url":"/paper/one-initialization-to-rule-them-all-fine","title":"Parameter Efficient Fine-tuning via Explained Variance Adaptation","date":"2024-10-09","arxiv_id":"2410.07170","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/lessons-learned-from-a-unifying-empirical","title":"Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition","date":"2024-09-24","arxiv_id":"2409.16434","repositories_listed":2,"syntology":null},{"url":"/paper/sam2rad-a-segmentation-model-for-medical","title":"Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts","date":"2024-09-10","arxiv_id":"2409.06821","repositories_listed":2,"syntology":null},{"url":"/paper/soft-language-prompts-for-language-transfer","title":"Soft Language Prompts for Language Transfer","date":"2024-07-02","arxiv_id":"2407.02317","repositories_listed":2,"syntology":null},{"url":"/paper/low-rank-few-shot-adaptation-of-vision","title":"Low-Rank Few-Shot Adaptation of Vision-Language Models","date":"2024-05-28","arxiv_id":"2405.18541","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/iisan-efficiently-adapting-multimodal","title":"IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT","date":"2024-04-02","arxiv_id":"2404.02059","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/advancing-parameter-efficiency-in-fine-tuning","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","date":"2024-02-23","arxiv_id":"2402.15179","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/kinit-at-semeval-2024-task-8-fine-tuned-llms","title":"KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection","date":"2024-02-21","arxiv_id":"2402.13671","repositories_listed":2,"syntology":null},{"url":"/paper/tunetables-context-optimization-for-scalable","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","date":"2024-02-17","arxiv_id":"2402.11137","repositories_listed":2,"syntology":{"n":17,"n_ran":10,"n_unverified":7,"n_pointer_only":0}}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}