---
title: "P-Tuning: Prompt Tuning Can Be Comparable to — Liu 2022"
description: "Fine-tuning a pretrained language model updates every weight."
authors: ["Xiao Liu", "Kaixuan Ji", "Yicheng Fu", "Weng Tam", "Zhengxiao Du", "Zhilin Yang", "Jie Tang"]
year: 2022
venue: "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)"
source: "https://aclanthology.org/2022.acl-short.8/"
doi: "10.18653/v1/2022.acl-short.8"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/liu-2022-p-tuning-prompt-tuning-can/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2022-p-tuning-prompt-tuning-can/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/page/3/) / P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks

# P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks

**Authors:** [Xiao Liu](https://md.research.elamur.ai/free/en/authors/xiao-liu/), [Kaixuan Ji](https://md.research.elamur.ai/free/en/authors/kaixuan-ji/), [Yicheng Fu](https://md.research.elamur.ai/free/en/authors/yicheng-fu/), Weng Tam, [Zhengxiao Du](https://md.research.elamur.ai/free/en/authors/zhengxiao-du/), [Zhilin Yang](https://md.research.elamur.ai/free/en/authors/zhilin-yang/), [Jie Tang](https://md.research.elamur.ai/free/en/authors/jie-tang/) · **Year:** 2022 · **Venue:** Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2022.acl-short.8/) · [PDF](https://aclanthology.org/2022.acl-short.8.pdf) · [DOI 10.18653/v1/2022.acl-short.8](https://doi.org/10.18653/v1/2022.acl-short.8) · [OpenAlex](https://openalex.org/W4285247752)

**Citations:** 775 citations (openalex-snapshot · 2026-10-14) · [238](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Fine-tuning a pretrained language model updates every weight. This takes a lot of training memory and requires storing a full model copy for each task. Earlier prompt tuning methods (Lester et al., 2021; P-tuning) train only continuous input embeddings on a frozen backbone. They come close to fine-tuning only at around 10B parameters and do poorly on sequence labeling. The authors present P-Tuning v2, an NLU-oriented implementation of Deep Prompt Tuning. It adds trainable prefix prompts at every transformer layer, not just the input. They also describe several practical choices:
- optional MLP reparameterization
- task-dependent prompt length
- optional multi-task pretraining of the prompts
- a randomly initialized linear classification head instead of a verbalizer

Experiments use fully supervised SuperGLUE plus NER, extractive QA (SQuAD) and SRL (CoNLL05/12), on frozen models from roughly 330M to 10B parameters. P-Tuning v2 performs on par with fine-tuning while training only 0.1–3% of the parameters per task. This makes it a cheap, general alternative and baseline.

## Key points
- **Backbones:** BERT-large, RoBERTa-large, DeBERTa-xlarge and GLM-xlarge/xxlarge (about 300M–10B parameters). Code is at github.com/THUDM/P-tuning-v2.
- **Prompt length:** Classification tasks work best with short prompts (under 20 tokens). Sequence labeling tasks prefer about 100 tokens.
- **Prompt depth (BERT-large):** Placing prompts in deeper layers beats placing them in early layers, given the same budget. On RTE, prompting only layers 17–24 nearly matches prompting all layers.
- **Classification head (RoBERTa-large):** A [CLS] linear head performs about as well as, or slightly better than, a verbalizer with LM head. Scores were SST-2 96.3 vs 95.8, RTE 88.4 vs 86.6, BoolQ 84.8 vs 84.6 and CB 96.4 vs 94.6.
- **Task-specific effects:** Single-layer prompt tuning behaves poorly on SQuAD 2.0, likely because of its unanswerable questions. Multi-task prompts help most tasks except QA.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

238 papers of our library cite it (of the 140884 whose bibliographies we read); 7 of them have a page here, 231 not yet.

- [Adapting Language Models to Compress Contexts](https://md.research.elamur.ai/free/en/papers/chevalier-2023-adapting-language-models-compress-contexts/)
- [Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications](https://md.research.elamur.ai/free/en/papers/kanjirangat-2025-exploring-data-parameter-efficient-strategies/)
- [A Comprehensive Overview of Large Language Models](https://md.research.elamur.ai/free/en/papers/naveed-2023-comprehensive-overview-large-language-models/)
- [To Write or to Automate Linguistic Prompts, That Is the Question](https://md.research.elamur.ai/free/en/papers/torron-2026-write-or-automate-linguistic-prompts/)
- [基于大语言模型的中文实体链接实证研究](https://md.research.elamur.ai/free/en/papers/xu-2025-empirical-study-chinese/)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://md.research.elamur.ai/free/en/papers/yang-2023-harnessing-power-llms-practice-survey/)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://md.research.elamur.ai/free/en/papers/zeng-2022-glm-130b-open-bilingual-pre/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{liu2022p,
  title = {{P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks}},
  author = {Liu, Xiao and Ji, Kaixuan and Fu, Yicheng and Tam, Weng and Du, Zhengxiao and Yang, Zhilin and Tang, Jie},
  booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  year = {2022},
  doi = {10.18653/v1/2022.acl-short.8},
  url = {https://doi.org/10.18653/v1/2022.acl-short.8}
}
```

- [← previous Out of One, Many: Using Language Models to Simulate Human Samples](https://md.research.elamur.ai/free/en/papers/argyle-2022-out-one-many-using-language/)
- [next → Pairwise Representation Learning for Event Coreference](https://md.research.elamur.ai/free/en/papers/yu-2022-pairwise-representation-learning-event-coreference/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/3/)

## References

26 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190. [find](https://scholar.google.com/scholar?q=Xiang+Lisa+Li+and+Percy+Liang%2E+2021%2E+Prefix%2Dtuning%3A+Optimizing+continuous+prompts+for+generation%2E+arXiv+preprint+arXiv%3A2101%2E00190%2E)
2. Tom B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165. [find](https://scholar.google.com/scholar?q=Tom+B+Brown%2C+Benjamin+Mann%2C+Nick+Ryder%2C+Melanie+Subbiah%2C+Jared+Kaplan%2C+Prafulla+Dhariwal%2C+Arvind+Neelakantan%2C+Pranav+Shyam%2C+Girish+Sastry%2C+Amanda+Askell%2C+et+al%2E+2020%2E+Language+models+are+few%2Dshot+lear)
3. Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2021. Gpt understands, too. arXiv:2103.10385. [find](https://scholar.google.com/scholar?q=Xiao+Liu%2C+Yanan+Zheng%2C+Zhengxiao+Du%2C+Ming+Ding%2C+Yujie+Qian%2C+Zhilin+Yang%2C+and+Jie+Tang%2E+2021%2E+Gpt+understands%2C+too%2E+arXiv%3A2103%2E10385%2E) [our card](https://md.research.elamur.ai/free/en/papers/liu-2021-gpt-understands-too/)
4. Xavier Carreras and Lluís Màrquez. 2004. Introduction to the CoNLL-2004 shared task: Semantic role labeling. In Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004, pages 89–97, Boston, Massachusetts, USA. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=Xavier+Carreras+and+Llu%C3%ADs+M%C3%A0rquez%2E+2004%2E+Introduction+to+the+CoNLL%2D2004+shared+task%3A+Semantic+role+labeling%2E+In+Proceedings+of+the+Eighth+Conference+on+Computational+Natural+Language+Learning+%28CoNLL%2D2)
5. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv e-prints. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+RoBERTa%3A+A+Robustly+Optimized+BERT+Pretraining+Approach%2E+a)
6. Sewon Min, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2021. Noisy channel language model prompting for few-shot text classification. arXiv preprint arXiv:2108.04106. [find](https://scholar.google.com/scholar?q=Sewon+Min%2C+Mike+Lewis%2C+Hannaneh+Hajishirzi%2C+and+Luke+Zettlemoyer%2E+2021%2E+Noisy+channel+language+model+prompting+for+few%2Dshot+text+classification%2E+arXiv+preprint+arXiv%3A2108%2E04106%2E) [our card](https://md.research.elamur.ai/free/en/papers/min-2021-noisy-channel-language-model-prompting/)
7. Xavier Carreras and Lluís Màrquez. 2005. Introduction to the CoNLL-2005 shared task: Semantic role labeling. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 152–164, Ann Arbor, Michigan. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xavier+Carreras+and+Llu%C3%ADs+M%C3%A0rquez%2E+2005%2E+Introduction+to+the+CoNLL%2D2005+shared+task%3A+Semantic+role+labeling%2E+In+Proceedings+of+the+Ninth+Conference+on+Computational+Natural+Language+Learning+%28CoNLL%2D20) [our card](https://md.research.elamur.ai/free/en/papers/carreras-2005-introduction-conll-2005-shared-task/)
8. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 1–40, Jeju Island, Korea. Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Sameer+Pradhan%2C+Alessandro+Moschitti%2C+Nianwen+Xue%2C+Olga+Uryupina%2C+and+Yuchen+Zhang%2E+2012%2E+CoNLL%2D2012+shared+task%3A+Modeling+multilingual+unrestricted+coreference+in+OntoNotes%2E+In+Joint+Conference+on+EM) [our card](https://md.research.elamur.ai/free/en/papers/pradhan-2012-conll-2012-shared-task-modeling/)
9. Xiang Chen, Xin Xie, Ningyu Zhang, Jiahuan Yan, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, and Huajun Chen. 2021. Adaprompt: Adaptive prompt-based finetuning for relation extraction. arXiv preprint arXiv:2104.07650. — [arXiv:2104.07650](https://arxiv.org/abs/2104.07650) [find](https://scholar.google.com/scholar?q=Xiang+Chen%2C+Xin+Xie%2C+Ningyu+Zhang%2C+Jiahuan+Yan%2C+Shumin+Deng%2C+Chuanqi+Tan%2C+Fei+Huang%2C+Luo+Si%2C+and+Huajun+Chen%2E+2021%2E+Adaprompt%3A+Adaptive+prompt%2Dbased+finetuning+for+relation+extraction%2E+arXiv+preprint+)
10. Guanghui Qin and Jason Eisner. 2021. Learning how to ask: Querying lms with mixtures of soft prompts. arXiv preprint arXiv:2104.06599. [find](https://scholar.google.com/scholar?q=Guanghui+Qin+and+Jason+Eisner%2E+2021%2E+Learning+how+to+ask%3A+Querying+lms+with+mixtures+of+soft+prompts%2E+arXiv+preprint+arXiv%3A2104%2E06599%2E) [our card](https://md.research.elamur.ai/free/en/papers/qin-2021-learning-ask-querying-lms-mixtures/)
11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2018%2E+Bert%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+arXiv+preprint+arXiv%3A1810%2E04805%2E)
12. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
13. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv e-prints. [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2018%2E+Bert%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+arXiv+e%2Dprints%2E)
14. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683. [find](https://scholar.google.com/scholar?q=Colin+Raffel%2C+Noam+Shazeer%2C+Adam+Roberts%2C+Katherine+Lee%2C+Sharan+Narang%2C+Michael+Matena%2C+Yanqi+Zhou%2C+Wei+Li%2C+and+Peter+J+Liu%2E+2019%2E+Exploring+the+limits+of+transfer+learning+with+a+unified+text%2Dto%2Dtext)
15. Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. 2021. All nlp tasks are generation tasks: A general pretraining framework. arXiv preprint arXiv:2103.10360. [find](https://scholar.google.com/scholar?q=Zhengxiao+Du%2C+Yujie+Qian%2C+Xiao+Liu%2C+Ming+Ding%2C+Jiezhong+Qiu%2C+Zhilin+Yang%2C+and+Jie+Tang%2E+2021%2E+All+nlp+tasks+are+generation+tasks%3A+A+general+pretraining+framework%2E+arXiv+preprint+arXiv%3A2103%2E10360%2E) [our card](https://md.research.elamur.ai/free/en/papers/du-2022-glm-general-language-model-pretraining/)
16. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. [find](https://scholar.google.com/scholar?q=Pranav+Rajpurkar%2C+Jian+Zhang%2C+Konstantin+Lopyrev%2C+and+Percy+Liang%2E+2016%2E+Squad%3A+100%2C000%2B+questions+for+machine+comprehension+of+text%2E) [our card](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/)
17. Tianyu Gao, Adam Fisch, and Danqi Chen. 2020. Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723. [find](https://scholar.google.com/scholar?q=Tianyu+Gao%2C+Adam+Fisch%2C+and+Danqi+Chen%2E+2020%2E+Making+pre%2Dtrained+language+models+better+few%2Dshot+learners%2E+arXiv+preprint+arXiv%3A2012%2E15723%2E) [our card](https://md.research.elamur.ai/free/en/papers/gao-2021-making-pre-trained-language-models/)
18. Erik F Sang and Fien De Meulder. 2003. Introduction to the conll-2003 shared task: Language-independent named entity recognition. arXiv preprint cs/0306050. [find](https://scholar.google.com/scholar?q=Erik+F+Sang+and+Fien+De+Meulder%2E+2003%2E+Introduction+to+the+conll%2D2003+shared+task%3A+Language%2Dindependent+named+entity+recognition%2E+arXiv+preprint+cs%2F0306050%2E)
19. Yuxian Gu, Xu Han, Zhiyuan Liu, and Minlie Huang. 2021. Ppt: Pre-trained prompt tuning for few-shot learning. arXiv preprint arXiv:2109.04332. [find](https://scholar.google.com/scholar?q=Yuxian+Gu%2C+Xu+Han%2C+Zhiyuan+Liu%2C+and+Minlie+Huang%2E+2021%2E+Ppt%3A+Pre%2Dtrained+prompt+tuning+for+few%2Dshot+learning%2E+arXiv+preprint+arXiv%3A2109%2E04332%2E) [our card](https://md.research.elamur.ai/free/en/papers/gu-2022-ppt-pre-trained-prompt-tuning/)
20. Timo Schick and Hinrich Schütze. 2020. It’s not just size that matters: Small language models are also few-shot learners. arXiv preprint arXiv:2009.07118. [find](https://scholar.google.com/scholar?q=Timo+Schick+and+Hinrich+Sch%C3%BCtze%2E+2020%2E+It%E2%80%99s+not+just+size+that+matters%3A+Small+language+models+are+also+few%2Dshot+learners%2E+arXiv+preprint+arXiv%3A2009%2E07118%2E) [our card](https://md.research.elamur.ai/free/en/papers/schick-2021-it-s-not-just-size/)
21. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. [find](https://scholar.google.com/scholar?q=Pengcheng+He%2C+Xiaodong+Liu%2C+Jianfeng+Gao%2C+and+Weizhu+Chen%2E+2020%2E+Deberta%3A+Decoding%2Denhanced+bert+with+disentangled+attention%2E) [our card](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/)
22. Taylor Shin, Yasaman Razeghi, Robert L Logan IV, Eric Wallace, and Sameer Singh. 2020. Autoprompt: Eliciting knowledge from language models with automatically generated prompts. arXiv preprint arXiv:2010.15980. [find](https://scholar.google.com/scholar?q=Taylor+Shin%2C+Yasaman+Razeghi%2C+Robert+L+Logan+IV%2C+Eric+Wallace%2C+and+Sameer+Singh%2E+2020%2E+Autoprompt%3A+Eliciting+knowledge+from+language+models+with+automatically+generated+prompts%2E+arXiv+preprint+arXiv%3A2) [our card](https://md.research.elamur.ai/free/en/papers/shin-2020-autoprompt-eliciting-knowledge-language-models/)
23. Boseop Kim, HyoungSeok Kim, Sang-Woo Lee, Gichang Lee, Donghyun Kwak, Dong Hyeon Jeon, Sunghyun Park, Sungju Kim, Seonhoon Kim, Dongpil Seo, et al. 2021. What changes can large-scale language models bring? intensive study on hyperclova: Billions-scale korean generative pretrained transformers. arXiv… [find](https://scholar.google.com/scholar?q=Boseop+Kim%2C+HyoungSeok+Kim%2C+Sang%2DWoo+Lee%2C+Gichang+Lee%2C+Donghyun+Kwak%2C+Dong+Hyeon+Jeon%2C+Sunghyun+Park%2C+Sungju+Kim%2C+Seonhoon+Kim%2C+Dongpil+Seo%2C+et+al%2E+2021%2E+What+changes+can+large%2Dscale+language+models+b)
24. Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems. In NeurIPS 2019, pages 3261– 3275. [find](https://scholar.google.com/scholar?q=Alex+Wang%2C+Yada+Pruksachatkun%2C+Nikita+Nangia%2C+Amanpreet+Singh%2C+Julian+Michael%2C+Felix+Hill%2C+Omer+Levy%2C+and+Samuel+R%2E+Bowman%2E+2019%2E+SuperGLUE%3A+A+Stickier+Benchmark+for+General%2DPurpose+Language+Understan) [our card](https://md.research.elamur.ai/free/en/papers/wang-2019-superglue-stickier-benchmark-general-purpose/)
25. Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691. [find](https://scholar.google.com/scholar?q=Brian+Lester%2C+Rami+Al%2DRfou%2C+and+Noah+Constant%2E+2021%2E+The+power+of+scale+for+parameter%2Defficient+prompt+tuning%2E+arXiv+preprint+arXiv%3A2104%2E08691%2E)
26. A Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. Superglue: A stickier benchmark for general-purpose language understanding systems. arXiv e-prints. [find](https://scholar.google.com/scholar?q=A+Alex+Wang%2C+Yada+Pruksachatkun%2C+Nikita+Nangia%2C+Amanpreet+Singh%2C+Julian+Michael%2C+Felix+Hill%2C+Omer+Levy%2C+and+Samuel+R%2E+Bowman%2E+2019%2E+Superglue%3A+A+stickier+benchmark+for+general%2Dpurpose+language+underst) [our card](https://md.research.elamur.ai/free/en/papers/wang-2019-superglue-stickier-benchmark-general-purpose/)