Prompt Contrastive Transformation: An Enhanced Strategy for Efficient Prompt Transfer in Natural Language Processing Article Swipe
Shu Zhao
,
Shiji Yang
,
Shicheng Tan
,
Zhen Yang
,
Chenxuan Mei
,
Zhen Duan
,
Yanping Zhang
,
Jie Chen
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1162/tacl.a.22
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1162/tacl.a.22
Prompt transfer is a transfer learning method based on prompt tuning, which enhances the parameter performance of prompts in target tasks by transferring source prompt embeddings. Among existing methods, weighted aggregation is effective and possesses the advantages of being lightweight and modular. However, these methods may transfer redundant or irrelevant information from the source prompts to the target prompt, leading to negative impacts. To alleviate this problem, we propose Prompt Contrastive Transformation (PCT), which achieves efficient prompt transfer through prompt contrastive transformation and attentional fusion. PCT transforms the source prompt into task-agnostic embedding and task-specific embeddings through singular value decomposition and contrastive learning, reducing information redundancy among source prompts. The attention module in PCT selects more effective task-specific embeddings and fuses them with task-agnostic embedding into the target prompt. Experimental results show that, despite tuning only 0.035% of task-specific parameters, PCT achieves improvements in prompt transfer for single target task adaptation across various NLP tasks.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1162/tacl.a.22
- https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.22/2540029/tacl.a.22.pdf
- OA Status
- diamond
- References
- 31
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4412930165
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4412930165Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1162/tacl.a.22Digital Object Identifier
- Title
-
Prompt Contrastive Transformation: An Enhanced Strategy for Efficient Prompt Transfer in Natural Language ProcessingWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-01Full publication date if available
- Authors
-
Shu Zhao, Shiji Yang, Shicheng Tan, Zhen Yang, Chenxuan Mei, Zhen Duan, Yanping Zhang, Jie ChenList of authors in order
- Landing page
-
https://doi.org/10.1162/tacl.a.22Publisher landing page
- PDF URL
-
https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.22/2540029/tacl.a.22.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.22/2540029/tacl.a.22.pdfDirect OA link when available
- Concepts
-
Computer science, Transformation (genetics), Transfer (computing), Natural language processing, Natural (archaeology), Artificial intelligence, History, Parallel computing, Biochemistry, Archaeology, Gene, ChemistryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
31Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4412930165 |
|---|---|
| doi | https://doi.org/10.1162/tacl.a.22 |
| ids.doi | https://doi.org/10.1162/tacl.a.22 |
| ids.openalex | https://openalex.org/W4412930165 |
| fwci | 0.0 |
| type | article |
| title | Prompt Contrastive Transformation: An Enhanced Strategy for Efficient Prompt Transfer in Natural Language Processing |
| biblio.issue | |
| biblio.volume | 13 |
| biblio.last_page | 860 |
| biblio.first_page | 848 |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998999834060669 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9998000264167786 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T12031 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9925000071525574 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Speech and dialogue systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8897916078567505 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C204241405 |
| concepts[1].level | 3 |
| concepts[1].score | 0.7484452724456787 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q461499 |
| concepts[1].display_name | Transformation (genetics) |
| concepts[2].id | https://openalex.org/C2776175482 |
| concepts[2].level | 2 |
| concepts[2].score | 0.55445796251297 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1195816 |
| concepts[2].display_name | Transfer (computing) |
| concepts[3].id | https://openalex.org/C204321447 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5479053854942322 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[3].display_name | Natural language processing |
| concepts[4].id | https://openalex.org/C2776608160 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5464767217636108 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q4785462 |
| concepts[4].display_name | Natural (archaeology) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.44397661089897156 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C95457728 |
| concepts[6].level | 0 |
| concepts[6].score | 0.08076632022857666 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q309 |
| concepts[6].display_name | History |
| concepts[7].id | https://openalex.org/C173608175 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[7].display_name | Parallel computing |
| concepts[8].id | https://openalex.org/C55493867 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[8].display_name | Biochemistry |
| concepts[9].id | https://openalex.org/C166957645 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[9].display_name | Archaeology |
| concepts[10].id | https://openalex.org/C104317684 |
| concepts[10].level | 2 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[10].display_name | Gene |
| concepts[11].id | https://openalex.org/C185592680 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[11].display_name | Chemistry |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8897916078567505 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/transformation |
| keywords[1].score | 0.7484452724456787 |
| keywords[1].display_name | Transformation (genetics) |
| keywords[2].id | https://openalex.org/keywords/transfer |
| keywords[2].score | 0.55445796251297 |
| keywords[2].display_name | Transfer (computing) |
| keywords[3].id | https://openalex.org/keywords/natural-language-processing |
| keywords[3].score | 0.5479053854942322 |
| keywords[3].display_name | Natural language processing |
| keywords[4].id | https://openalex.org/keywords/natural |
| keywords[4].score | 0.5464767217636108 |
| keywords[4].display_name | Natural (archaeology) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.44397661089897156 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/history |
| keywords[6].score | 0.08076632022857666 |
| keywords[6].display_name | History |
| language | en |
| locations[0].id | doi:10.1162/tacl.a.22 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S2729999759 |
| locations[0].source.issn | 2307-387X |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2307-387X |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | Transactions of the Association for Computational Linguistics |
| locations[0].source.host_organization | https://openalex.org/P4310320244 |
| locations[0].source.host_organization_name | Association for Computational Linguistics |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320244 |
| locations[0].source.host_organization_lineage_names | Association for Computational Linguistics |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.22/2540029/tacl.a.22.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Transactions of the Association for Computational Linguistics |
| locations[0].landing_page_url | https://doi.org/10.1162/tacl.a.22 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5100661274 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7647-3603 |
| authorships[0].author.display_name | Shu Zhao |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I143868143 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[0].institutions[0].id | https://openalex.org/I143868143 |
| authorships[0].institutions[0].ror | https://ror.org/05th6yx34 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I143868143 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Anhui University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Shu Zhao |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[1].author.id | https://openalex.org/A5057475400 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Shiji Yang |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I143868143 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[1].institutions[0].id | https://openalex.org/I143868143 |
| authorships[1].institutions[0].ror | https://ror.org/05th6yx34 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I143868143 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Anhui University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Shiji Yang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[2].author.id | https://openalex.org/A5060604624 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Shicheng Tan |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I143868143 |
| authorships[2].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[2].institutions[0].id | https://openalex.org/I143868143 |
| authorships[2].institutions[0].ror | https://ror.org/05th6yx34 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I143868143 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Anhui University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Shicheng Tan |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[3].author.id | https://openalex.org/A5115602239 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-6058-0217 |
| authorships[3].author.display_name | Zhen Yang |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I143868143 |
| authorships[3].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[3].institutions[0].id | https://openalex.org/I143868143 |
| authorships[3].institutions[0].ror | https://ror.org/05th6yx34 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I143868143 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Anhui University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhen Yang |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[4].author.id | https://openalex.org/A5113073264 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Chenxuan Mei |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I143868143 |
| authorships[4].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[4].institutions[0].id | https://openalex.org/I143868143 |
| authorships[4].institutions[0].ror | https://ror.org/05th6yx34 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I143868143 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Anhui University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Congyao Mei |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[5].author.id | https://openalex.org/A5053714284 |
| authorships[5].author.orcid | https://orcid.org/0009-0004-0252-4956 |
| authorships[5].author.display_name | Zhen Duan |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I143868143 |
| authorships[5].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[5].institutions[0].id | https://openalex.org/I143868143 |
| authorships[5].institutions[0].ror | https://ror.org/05th6yx34 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I143868143 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | Anhui University |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zhen Duan |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[6].author.id | https://openalex.org/A5100430706 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-6048-8891 |
| authorships[6].author.display_name | Yanping Zhang |
| authorships[6].countries | CN |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I143868143 |
| authorships[6].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[6].institutions[0].id | https://openalex.org/I143868143 |
| authorships[6].institutions[0].ror | https://ror.org/05th6yx34 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I143868143 |
| authorships[6].institutions[0].country_code | CN |
| authorships[6].institutions[0].display_name | Anhui University |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Yanping Zhang |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[7].author.id | https://openalex.org/A5100332831 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-6474-9238 |
| authorships[7].author.display_name | Jie Chen |
| authorships[7].countries | CN |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I143868143 |
| authorships[7].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Anhui University, China. [email protected] |
| authorships[7].institutions[0].id | https://openalex.org/I143868143 |
| authorships[7].institutions[0].ror | https://ror.org/05th6yx34 |
| authorships[7].institutions[0].type | education |
| authorships[7].institutions[0].lineage | https://openalex.org/I143868143 |
| authorships[7].institutions[0].country_code | CN |
| authorships[7].institutions[0].display_name | Anhui University |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Jie Chen |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | School of Computer Science and Technology, Anhui University, China. [email protected] |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.22/2540029/tacl.a.22.pdf |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Prompt Contrastive Transformation: An Enhanced Strategy for Efficient Prompt Transfer in Natural Language Processing |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998999834060669 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W4283262748, https://openalex.org/W2353644209, https://openalex.org/W2593663830, https://openalex.org/W2348743188, https://openalex.org/W2902317490, https://openalex.org/W2463239216, https://openalex.org/W4387423451, https://openalex.org/W2502773048, https://openalex.org/W2025460258, https://openalex.org/W3204019825 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1162/tacl.a.22 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2729999759 |
| best_oa_location.source.issn | 2307-387X |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2307-387X |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | Transactions of the Association for Computational Linguistics |
| best_oa_location.source.host_organization | https://openalex.org/P4310320244 |
| best_oa_location.source.host_organization_name | Association for Computational Linguistics |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320244 |
| best_oa_location.source.host_organization_lineage_names | Association for Computational Linguistics |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.22/2540029/tacl.a.22.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Transactions of the Association for Computational Linguistics |
| best_oa_location.landing_page_url | https://doi.org/10.1162/tacl.a.22 |
| primary_location.id | doi:10.1162/tacl.a.22 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S2729999759 |
| primary_location.source.issn | 2307-387X |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2307-387X |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | Transactions of the Association for Computational Linguistics |
| primary_location.source.host_organization | https://openalex.org/P4310320244 |
| primary_location.source.host_organization_name | Association for Computational Linguistics |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320244 |
| primary_location.source.host_organization_lineage_names | Association for Computational Linguistics |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.22/2540029/tacl.a.22.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Transactions of the Association for Computational Linguistics |
| primary_location.landing_page_url | https://doi.org/10.1162/tacl.a.22 |
| publication_date | 2025-01-01 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4385573776, https://openalex.org/W4401978639, https://openalex.org/W6853251322, https://openalex.org/W4322766882, https://openalex.org/W2988421999, https://openalex.org/W4385570210, https://openalex.org/W6759579507, https://openalex.org/W3168867926, https://openalex.org/W4385573170, https://openalex.org/W4401042757, https://openalex.org/W2788496822, https://openalex.org/W6631190155, https://openalex.org/W4398191950, https://openalex.org/W4205991051, https://openalex.org/W4229005744, https://openalex.org/W3174770825, https://openalex.org/W3166846774, https://openalex.org/W6769627184, https://openalex.org/W3194676777, https://openalex.org/W4287891024, https://openalex.org/W3205717164, https://openalex.org/W6762392948, https://openalex.org/W6750615492, https://openalex.org/W3213415226, https://openalex.org/W6851130092, https://openalex.org/W4392904448, https://openalex.org/W3176828726, https://openalex.org/W6685053522, https://openalex.org/W2932893307, https://openalex.org/W4392939508, https://openalex.org/W4288089799 |
| referenced_works_count | 31 |
| abstract_inverted_index.a | 4 |
| abstract_inverted_index.To | 64 |
| abstract_inverted_index.by | 22 |
| abstract_inverted_index.in | 19, 113, 144 |
| abstract_inverted_index.is | 3, 32 |
| abstract_inverted_index.of | 17, 38, 138 |
| abstract_inverted_index.on | 9 |
| abstract_inverted_index.or | 49 |
| abstract_inverted_index.to | 56, 61 |
| abstract_inverted_index.we | 68 |
| abstract_inverted_index.NLP | 154 |
| abstract_inverted_index.PCT | 86, 114, 141 |
| abstract_inverted_index.The | 110 |
| abstract_inverted_index.and | 34, 41, 83, 94, 101, 120 |
| abstract_inverted_index.for | 147 |
| abstract_inverted_index.may | 46 |
| abstract_inverted_index.the | 14, 36, 53, 57, 88, 127 |
| abstract_inverted_index.from | 52 |
| abstract_inverted_index.into | 91, 126 |
| abstract_inverted_index.more | 116 |
| abstract_inverted_index.only | 136 |
| abstract_inverted_index.show | 132 |
| abstract_inverted_index.task | 150 |
| abstract_inverted_index.them | 122 |
| abstract_inverted_index.this | 66 |
| abstract_inverted_index.with | 123 |
| abstract_inverted_index.Among | 27 |
| abstract_inverted_index.among | 107 |
| abstract_inverted_index.based | 8 |
| abstract_inverted_index.being | 39 |
| abstract_inverted_index.fuses | 121 |
| abstract_inverted_index.tasks | 21 |
| abstract_inverted_index.that, | 133 |
| abstract_inverted_index.these | 44 |
| abstract_inverted_index.value | 99 |
| abstract_inverted_index.which | 12, 74 |
| abstract_inverted_index.(PCT), | 73 |
| abstract_inverted_index.0.035% | 137 |
| abstract_inverted_index.Prompt | 1, 70 |
| abstract_inverted_index.across | 152 |
| abstract_inverted_index.method | 7 |
| abstract_inverted_index.module | 112 |
| abstract_inverted_index.prompt | 10, 25, 77, 80, 90, 145 |
| abstract_inverted_index.single | 148 |
| abstract_inverted_index.source | 24, 54, 89, 108 |
| abstract_inverted_index.target | 20, 58, 128, 149 |
| abstract_inverted_index.tasks. | 155 |
| abstract_inverted_index.tuning | 135 |
| abstract_inverted_index.despite | 134 |
| abstract_inverted_index.fusion. | 85 |
| abstract_inverted_index.leading | 60 |
| abstract_inverted_index.methods | 45 |
| abstract_inverted_index.prompt, | 59 |
| abstract_inverted_index.prompt. | 129 |
| abstract_inverted_index.prompts | 18, 55 |
| abstract_inverted_index.propose | 69 |
| abstract_inverted_index.results | 131 |
| abstract_inverted_index.selects | 115 |
| abstract_inverted_index.through | 79, 97 |
| abstract_inverted_index.tuning, | 11 |
| abstract_inverted_index.various | 153 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.However, | 43 |
| abstract_inverted_index.achieves | 75, 142 |
| abstract_inverted_index.enhances | 13 |
| abstract_inverted_index.existing | 28 |
| abstract_inverted_index.impacts. | 63 |
| abstract_inverted_index.learning | 6 |
| abstract_inverted_index.methods, | 29 |
| abstract_inverted_index.modular. | 42 |
| abstract_inverted_index.negative | 62 |
| abstract_inverted_index.problem, | 67 |
| abstract_inverted_index.prompts. | 109 |
| abstract_inverted_index.reducing | 104 |
| abstract_inverted_index.singular | 98 |
| abstract_inverted_index.transfer | 2, 5, 47, 78, 146 |
| abstract_inverted_index.weighted | 30 |
| abstract_inverted_index.alleviate | 65 |
| abstract_inverted_index.attention | 111 |
| abstract_inverted_index.effective | 33, 117 |
| abstract_inverted_index.efficient | 76 |
| abstract_inverted_index.embedding | 93, 125 |
| abstract_inverted_index.learning, | 103 |
| abstract_inverted_index.parameter | 15 |
| abstract_inverted_index.possesses | 35 |
| abstract_inverted_index.redundant | 48 |
| abstract_inverted_index.adaptation | 151 |
| abstract_inverted_index.advantages | 37 |
| abstract_inverted_index.embeddings | 96, 119 |
| abstract_inverted_index.irrelevant | 50 |
| abstract_inverted_index.redundancy | 106 |
| abstract_inverted_index.transforms | 87 |
| abstract_inverted_index.Contrastive | 71 |
| abstract_inverted_index.aggregation | 31 |
| abstract_inverted_index.attentional | 84 |
| abstract_inverted_index.contrastive | 81, 102 |
| abstract_inverted_index.embeddings. | 26 |
| abstract_inverted_index.information | 51, 105 |
| abstract_inverted_index.lightweight | 40 |
| abstract_inverted_index.parameters, | 140 |
| abstract_inverted_index.performance | 16 |
| abstract_inverted_index.Experimental | 130 |
| abstract_inverted_index.improvements | 143 |
| abstract_inverted_index.transferring | 23 |
| abstract_inverted_index.decomposition | 100 |
| abstract_inverted_index.task-agnostic | 92, 124 |
| abstract_inverted_index.task-specific | 95, 118, 139 |
| abstract_inverted_index.Transformation | 72 |
| abstract_inverted_index.transformation | 82 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile.value | 0.14563127 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |