The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks
Open accessAbstract
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 (CITATION) 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
Self-citationSQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Li, X. L., & Liang, P. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.353 · Cited by 2,473
Research works printed but not linked: 4
- P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks https://aclanthology.org/2022.acl-short.8/ (Liu et al., ACL 2022)
- P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks (Liu et al., ACL 2022)
- Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Tam, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2022. P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 61–68, Dublin, Ireland. Association for Computational Linguistics.
- ACL materials are Copyright © 1963–2026 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
Cited by
Sorted by citations
Items 801–823 of 823
SymCLIP: Symmetric Prompting with Adaptive Semantic Labeling for Multi-Intent RecognitionPreprint
Wu, S., & Ma, H. (2026) · Research Square · doi:10.21203/rs.3.rs-10542927/v1
Fang, M., Lin, S., & Shang, W. (2026) · International Symposium on E-CARGO and Applications (E-CARGO) · doi:10.1109/e-cargo70110.2026.11671066
Duan, Y., Li, J., Goli, N., Ishimura, Y., Li, Y., Tida, U. R., & Jia, Z. (2026) · High-Confidence Computing · doi:10.1016/j.hcc.2026.100428
Toward an algebraic framework for operator-based prompt engineering in large language models
Olaymi, S. E. Z. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12434-z
Alkhadour, W. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0136-3.ch008
Wu, S., Wang, Y., & Zhang, H. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03286-z
FAMoE-ST: Hierarchically Frozen Attention with Hybrid-Memory Experts for Traffic-Flow Forecasting
Li, C., Wang, Z., & Zhu, F. (2026) · Applied Sciences · doi:10.3390/app16189140
Goenka, S., Khekare, G. S., Adhikari, P., Tyagi, A., & Tyagi, D. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1891737
Evaluating large language models for domain-specific scholarly metadata classification
Haris, M., & Badar, M. (2026) · Frontiers in Research Metrics and Analytics · doi:10.3389/frma.2026.1882130
Chen, X., & Yang, J. (2026) · International Conference on Machine Learning and Intelligent Computing · doi:10.1145/3829441.3829510
Residual Information Network Editing for Persona Steering in Frozen Language Models
Pratama, A. A. Y., Kliveson, C., Elhan, A., & Hidayaturrahman (2026) · International Conference on Information Management and Technology (ICIMTech) · doi:10.1109/icimtech202671078.2026.11699070
Scale-Aware Koopman-Structured PEFT: From Weight-Space Adapters to Activation-Space Dynamics
He, C., Zhang, C., Wang, J., & Li, H. (2026) · International Conference on Data-driven Optimization of Complex Systems (DOCS) · doi:10.1109/docs70981.2026.11698635
A Comprehensive Dataset and Benchmark for Empathetic Responses in Online Communities
Qi, S., Lyu, J., Liao, M., Xiang, R., & Li, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5696-9_16
CoPT: Context-based prompt tuning for pretrained language model via test-time adaptation
Shin, J., Lee, H. E., Cho, H., & Kim, J. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134712
PrefixGuard: Lightweight LLMs for Hate Speech and Sexism Detection
Dorleon, G., & Shujaa, S. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729560
Adolescent Psychological Support Dialogue Generation Model of Domain Data-Driven
Wu, D., Zhang, T., & Wang, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728528
Dai, J., & Xu, X. (2026) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2026.105370
LLaMIA: Few-Shot Medical Image Lesion Localization Analysis with Large Language Models
Xie, R., Zeng, A., Pan, D., & Zhao, Y. (2026) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-026-00871-2
Lv, H., 谭开忠, Wang, S., Mo, Z., & Ding, Y. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.104046
Prior Knowledge-Guided Prototypical Network for Few-Shot Relation Extraction
Gong, W., Zhou, Q., & Wu, Y. (2026) · International Journal of Computational Intelligence and Applications · doi:10.1142/s1469026826500665
An Interactive Management Framework for Engine Product Quality Based on the Large Language Model
Sun, A., & Mao, Z. (2026) · IEEE International Conference on Artificial Intelligence, Computer Science and Information Processing (AICSIP) · doi:10.1109/aicsip69702.2026.11743980
SigLIP-HGC: Hierarchical Image Captioning via Gated Cross-Scale Fusion
Hani, A., Tagougui, N., & Kherallah, M. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.10.082
Metadata
- Authors
- Liu, X., Ji, K., Fu, Y., Tam, W., Du, Z., Yang, Z., & Tang, J.
- Affiliations
- Beijing Academy of Artificial Intelligence (CN)
- Tsinghua University (CN)
- Shanghai Qi Zhi Institute (CN)
- Corresponding author
- Liu, Xiao
- Venue
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Published
- 2022
- Pages
- 61-68
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4285247752
- Cited by
- 810
- References
- 29
- Citations by year
- 2026: 112 · 2025: 232 · 2024: 265 · 2023: 173 · 2022: 28
- FWCI
- 96.50
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Funders
- National Natural Science Foundation of China (61836013, 61825602)
- Tsinghua University
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- prompt tuning, fine-tuning alternatives, natural language understanding, sequence labeling, model scale, memory efficiency, parameter-efficient training
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
