{"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/p-tuning-v2-prompt-tuning-can-be-comparable","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","arxiv_id":"2110.07602","date":"2021-10-14","proceeding":null,"authors":["Xiao Liu","Kaixuan Ji","Yicheng Fu","Weng Lam Tam","Zhengxiao Du","Zhilin Yang","Jie Tang"],"abstract":"Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU, prior work reveals that prompt tuning does not perform well for normal-sized pretrained models. We also find that existing methods of prompt tuning cannot handle hard sequence labeling tasks, indicating a lack of universality. We present a novel empirical finding that properly optimized prompt tuning can be universally effective across a wide range of model scales and NLU tasks. It matches the performance of finetuning while having only 0.1%-3% tuned parameters. Our method P-Tuning v2 is an implementation of Deep Prompt Tuning \\cite{li2021prefix,qin2021learning} optimized and adapted for NLU. Given the universality and simplicity of P-Tuning v2, we believe it can serve as an alternative to finetuning and a strong baseline for future research.Our code and data are released at https://github.com/THUDM/P-tuning-v2.","url_abs":"https://arxiv.org/abs/2110.07602v3","url_pdf":"https://arxiv.org/pdf/2110.07602v3.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":"p-tuning-v2-prompt-tuning-can-be-comparable","repo_url":"https://github.com/thudm/p-tuning-v2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"p-tuning-v2-prompt-tuning-can-be-comparable","repo_url":"https://github.com/THUDM/P-tuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"p-tuning-v2-prompt-tuning-can-be-comparable","repo_url":"https://github.com/jellyfish042/rwkv-statetuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"p-tuning-v2-prompt-tuning-can-be-comparable","repo_url":"https://github.com/liucongg/chatglm-finetuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"p-tuning-v2-prompt-tuning-can-be-comparable","repo_url":"https://github.com/zhanglab-aim/lingo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.07602","atlas_url":"https://app.syntology.ai/?focus=2110.07602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07602"}},"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/zhanglab-aim/lingo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jellyfish042/rwkv-statetuning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/THUDM/P-tuning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liucongg/chatglm-finetuning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/p-tuning-v2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"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":0,"samples":[{"code_sha256_prefix":"143ddd4a9eb16ee5","entry":"extract_integer","repo":"jellyfish042/rwkv-statetuning","repo_kind":"listed","path":"train_state.py","file_url":"https://github.com/jellyfish042/rwkv-statetuning/blob/HEAD/train_state.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"143ddd4a9eb16ee5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}