Automated Few-Shot Classification with Instruction-Finetuned Language Models Article Swipe
Rami Aly
,
Xingjian Shi
,
Kaixiang Lin
,
Aston Zhang
,
Andrew Gordon Wilson
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2023.findings-emnlp.158
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2023.findings-emnlp.158
A particularly successful class of approaches for few-shot learning combines language models with prompts - hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires domain knowledge and substantial guesswork. We observe, in the context of classification tasks, that instruction finetuned language models are remarkably robust towards some dimensions of a prompt’s design. We subsequently propose a simple method to eliminate the need for handcrafted prompts, named AuT-Few. This approach consists of (i) a prompt retrieval module that selects suitable task instructions from the instruction-tuning knowledge base, and (ii) the generation of two distinct, semantically meaningful, class descriptions and a selection mechanism via cross-validation. Over 12 datasets, spanning 8 classification tasks, we show that AuT-Few outperforms current state-of-the-art few-shot learning methods. Moreover, AuT-Few is the best ranking method across datasets on the RAFT few-shot benchmark. Notably, these results are achieved without task-specific handcrafted prompts on unseen tasks.
Related Topics
Concepts
Computer science
Artificial intelligence
Benchmark (surveying)
Task (project management)
Class (philosophy)
Context (archaeology)
Ranking (information retrieval)
Natural language processing
Selection (genetic algorithm)
Complement (music)
Language model
Machine learning
Complementation
Paleontology
Economics
Gene
Geography
Biochemistry
Biology
Management
Geodesy
Phenotype
Chemistry
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.18653/v1/2023.findings-emnlp.158
- https://aclanthology.org/2023.findings-emnlp.158.pdf
- OA Status
- gold
- Cited By
- 2
- References
- 55
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4389519601
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4389519601Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.18653/v1/2023.findings-emnlp.158Digital Object Identifier
- Title
-
Automated Few-Shot Classification with Instruction-Finetuned Language ModelsWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-01-01Full publication date if available
- Authors
-
Rami Aly, Xingjian Shi, Kaixiang Lin, Aston Zhang, Andrew Gordon WilsonList of authors in order
- Landing page
-
https://doi.org/10.18653/v1/2023.findings-emnlp.158Publisher landing page
- PDF URL
-
https://aclanthology.org/2023.findings-emnlp.158.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://aclanthology.org/2023.findings-emnlp.158.pdfDirect OA link when available
- Concepts
-
Computer science, Artificial intelligence, Benchmark (surveying), Task (project management), Class (philosophy), Context (archaeology), Ranking (information retrieval), Natural language processing, Selection (genetic algorithm), Complement (music), Language model, Machine learning, Complementation, Paleontology, Economics, Gene, Geography, Biochemistry, Biology, Management, Geodesy, Phenotype, ChemistryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2023: 1Per-year citation counts (last 5 years)
- References (count)
-
55Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4389519601 |
|---|---|
| doi | https://doi.org/10.18653/v1/2023.findings-emnlp.158 |
| ids.doi | https://doi.org/10.18653/v1/2023.findings-emnlp.158 |
| ids.openalex | https://openalex.org/W4389519601 |
| fwci | 0.51088578 |
| type | article |
| title | Automated Few-Shot Classification with Instruction-Finetuned Language Models |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 2432 |
| biblio.first_page | 2414 |
| 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 | 0.9997000098228455 |
| 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 | 0.9986000061035156 |
| 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/T13629 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9886999726295471 |
| 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 | Text Readability and Simplification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.9316067695617676 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.6170933246612549 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C185798385 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6094590425491333 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1161707 |
| concepts[2].display_name | Benchmark (surveying) |
| concepts[3].id | https://openalex.org/C2780451532 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6057378053665161 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[3].display_name | Task (project management) |
| concepts[4].id | https://openalex.org/C2777212361 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5508942604064941 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[4].display_name | Class (philosophy) |
| concepts[5].id | https://openalex.org/C2779343474 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5418863892555237 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[5].display_name | Context (archaeology) |
| concepts[6].id | https://openalex.org/C189430467 |
| concepts[6].level | 2 |
| concepts[6].score | 0.48787784576416016 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7293293 |
| concepts[6].display_name | Ranking (information retrieval) |
| concepts[7].id | https://openalex.org/C204321447 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4487541615962982 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[7].display_name | Natural language processing |
| concepts[8].id | https://openalex.org/C81917197 |
| concepts[8].level | 2 |
| concepts[8].score | 0.43902334570884705 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q628760 |
| concepts[8].display_name | Selection (genetic algorithm) |
| concepts[9].id | https://openalex.org/C112313634 |
| concepts[9].level | 5 |
| concepts[9].score | 0.4358009099960327 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7886648 |
| concepts[9].display_name | Complement (music) |
| concepts[10].id | https://openalex.org/C137293760 |
| concepts[10].level | 2 |
| concepts[10].score | 0.42787712812423706 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[10].display_name | Language model |
| concepts[11].id | https://openalex.org/C119857082 |
| concepts[11].level | 1 |
| concepts[11].score | 0.3616601824760437 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[11].display_name | Machine learning |
| concepts[12].id | https://openalex.org/C188082640 |
| concepts[12].level | 4 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1780899 |
| concepts[12].display_name | Complementation |
| concepts[13].id | https://openalex.org/C151730666 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[13].display_name | Paleontology |
| concepts[14].id | https://openalex.org/C162324750 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[14].display_name | Economics |
| concepts[15].id | https://openalex.org/C104317684 |
| concepts[15].level | 2 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[15].display_name | Gene |
| concepts[16].id | https://openalex.org/C205649164 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[16].display_name | Geography |
| concepts[17].id | https://openalex.org/C55493867 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[17].display_name | Biochemistry |
| concepts[18].id | https://openalex.org/C86803240 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[18].display_name | Biology |
| concepts[19].id | https://openalex.org/C187736073 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[19].display_name | Management |
| concepts[20].id | https://openalex.org/C13280743 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q131089 |
| concepts[20].display_name | Geodesy |
| concepts[21].id | https://openalex.org/C127716648 |
| concepts[21].level | 3 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q104053 |
| concepts[21].display_name | Phenotype |
| concepts[22].id | https://openalex.org/C185592680 |
| concepts[22].level | 0 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[22].display_name | Chemistry |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.9316067695617676 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.6170933246612549 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/benchmark |
| keywords[2].score | 0.6094590425491333 |
| keywords[2].display_name | Benchmark (surveying) |
| keywords[3].id | https://openalex.org/keywords/task |
| keywords[3].score | 0.6057378053665161 |
| keywords[3].display_name | Task (project management) |
| keywords[4].id | https://openalex.org/keywords/class |
| keywords[4].score | 0.5508942604064941 |
| keywords[4].display_name | Class (philosophy) |
| keywords[5].id | https://openalex.org/keywords/context |
| keywords[5].score | 0.5418863892555237 |
| keywords[5].display_name | Context (archaeology) |
| keywords[6].id | https://openalex.org/keywords/ranking |
| keywords[6].score | 0.48787784576416016 |
| keywords[6].display_name | Ranking (information retrieval) |
| keywords[7].id | https://openalex.org/keywords/natural-language-processing |
| keywords[7].score | 0.4487541615962982 |
| keywords[7].display_name | Natural language processing |
| keywords[8].id | https://openalex.org/keywords/selection |
| keywords[8].score | 0.43902334570884705 |
| keywords[8].display_name | Selection (genetic algorithm) |
| keywords[9].id | https://openalex.org/keywords/complement |
| keywords[9].score | 0.4358009099960327 |
| keywords[9].display_name | Complement (music) |
| keywords[10].id | https://openalex.org/keywords/language-model |
| keywords[10].score | 0.42787712812423706 |
| keywords[10].display_name | Language model |
| keywords[11].id | https://openalex.org/keywords/machine-learning |
| keywords[11].score | 0.3616601824760437 |
| keywords[11].display_name | Machine learning |
| language | en |
| locations[0].id | doi:10.18653/v1/2023.findings-emnlp.158 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://aclanthology.org/2023.findings-emnlp.158.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-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 | Findings of the Association for Computational Linguistics: EMNLP 2023 |
| locations[0].landing_page_url | https://doi.org/10.18653/v1/2023.findings-emnlp.158 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5030953897 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Rami Aly |
| authorships[0].countries | GB |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I241749 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Cambridge |
| authorships[0].institutions[0].id | https://openalex.org/I241749 |
| authorships[0].institutions[0].ror | https://ror.org/013meh722 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I241749 |
| authorships[0].institutions[0].country_code | GB |
| authorships[0].institutions[0].display_name | University of Cambridge |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Rami Aly |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of Cambridge |
| authorships[1].author.id | https://openalex.org/A5091515481 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2700-7742 |
| authorships[1].author.display_name | Xingjian Shi |
| authorships[1].affiliations[0].raw_affiliation_string | Boson AI |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xingjian Shi |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Boson AI |
| authorships[2].author.id | https://openalex.org/A5100443077 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-8626-8934 |
| authorships[2].author.display_name | Kaixiang Lin |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I1311688040 |
| authorships[2].affiliations[0].raw_affiliation_string | Amazon Web Services |
| authorships[2].institutions[0].id | https://openalex.org/I1311688040 |
| authorships[2].institutions[0].ror | https://ror.org/04mv4n011 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I1311688040 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Amazon (United States) |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kaixiang Lin |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Amazon Web Services |
| authorships[3].author.id | https://openalex.org/A5049841140 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Aston Zhang |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I1311688040 |
| authorships[3].affiliations[0].raw_affiliation_string | Amazon Web Services |
| authorships[3].institutions[0].id | https://openalex.org/I1311688040 |
| authorships[3].institutions[0].ror | https://ror.org/04mv4n011 |
| authorships[3].institutions[0].type | company |
| authorships[3].institutions[0].lineage | https://openalex.org/I1311688040 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Amazon (United States) |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Aston Zhang |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Amazon Web Services |
| authorships[4].author.id | https://openalex.org/A5101694421 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-2011-3315 |
| authorships[4].author.display_name | Andrew Gordon Wilson |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I1311688040 |
| authorships[4].affiliations[0].raw_affiliation_string | Amazon Web Services |
| authorships[4].affiliations[1].institution_ids | https://openalex.org/I57206974 |
| authorships[4].affiliations[1].raw_affiliation_string | New York University |
| authorships[4].institutions[0].id | https://openalex.org/I1311688040 |
| authorships[4].institutions[0].ror | https://ror.org/04mv4n011 |
| authorships[4].institutions[0].type | company |
| authorships[4].institutions[0].lineage | https://openalex.org/I1311688040 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | Amazon (United States) |
| authorships[4].institutions[1].id | https://openalex.org/I57206974 |
| authorships[4].institutions[1].ror | https://ror.org/0190ak572 |
| authorships[4].institutions[1].type | education |
| authorships[4].institutions[1].lineage | https://openalex.org/I57206974 |
| authorships[4].institutions[1].country_code | US |
| authorships[4].institutions[1].display_name | New York University |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Andrew Wilson |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Amazon Web Services, New York University |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://aclanthology.org/2023.findings-emnlp.158.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Automated Few-Shot Classification with Instruction-Finetuned Language Models |
| 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 | 0.9997000098228455 |
| 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/W2378211422, https://openalex.org/W4321353415, https://openalex.org/W2745001401, https://openalex.org/W2130974462, https://openalex.org/W2028665553, https://openalex.org/W2086519370, https://openalex.org/W972276598, https://openalex.org/W4246352526, https://openalex.org/W2121910908, https://openalex.org/W1494981348 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.18653/v1/2023.findings-emnlp.158 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://aclanthology.org/2023.findings-emnlp.158.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-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 | Findings of the Association for Computational Linguistics: EMNLP 2023 |
| best_oa_location.landing_page_url | https://doi.org/10.18653/v1/2023.findings-emnlp.158 |
| primary_location.id | doi:10.18653/v1/2023.findings-emnlp.158 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://aclanthology.org/2023.findings-emnlp.158.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-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 | Findings of the Association for Computational Linguistics: EMNLP 2023 |
| primary_location.landing_page_url | https://doi.org/10.18653/v1/2023.findings-emnlp.158 |
| publication_date | 2023-01-01 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W6601671322, https://openalex.org/W4313680121, https://openalex.org/W3168867926, https://openalex.org/W3201983976, https://openalex.org/W2806183494, https://openalex.org/W3103764297, https://openalex.org/W2956105246, https://openalex.org/W4206155854, https://openalex.org/W3172642864, https://openalex.org/W4287887247, https://openalex.org/W3216866458, https://openalex.org/W4287122891, https://openalex.org/W4286953959, https://openalex.org/W4308244910, https://openalex.org/W2953005365, https://openalex.org/W4280534475, https://openalex.org/W4285178342, https://openalex.org/W3120074043, https://openalex.org/W3198599617, https://openalex.org/W4307079201, https://openalex.org/W2963341956, https://openalex.org/W2891575196, https://openalex.org/W3186492090, https://openalex.org/W3001279689, https://openalex.org/W4297795751, https://openalex.org/W4224875176, https://openalex.org/W4286987939, https://openalex.org/W2790235966, https://openalex.org/W4229023857, https://openalex.org/W3166846774, https://openalex.org/W3174784402, https://openalex.org/W4285107336, https://openalex.org/W3026404337, https://openalex.org/W3188542058, https://openalex.org/W4285286749, https://openalex.org/W4224275713, https://openalex.org/W1599016936, https://openalex.org/W2251939518, https://openalex.org/W2160536005, https://openalex.org/W4286859764, https://openalex.org/W2953320089, https://openalex.org/W3205068155, https://openalex.org/W4312107783, https://openalex.org/W4303648858, https://openalex.org/W3098267758, https://openalex.org/W2129767020, https://openalex.org/W2970641574, https://openalex.org/W2954226438, https://openalex.org/W4283026156, https://openalex.org/W3034850762, https://openalex.org/W3045492832, https://openalex.org/W3173777717, https://openalex.org/W2130158090, https://openalex.org/W4296959557, https://openalex.org/W3205717164 |
| referenced_works_count | 55 |
| abstract_inverted_index.- | 14 |
| abstract_inverted_index.8 | 115 |
| abstract_inverted_index.A | 0 |
| abstract_inverted_index.a | 57, 63, 80, 106 |
| abstract_inverted_index.12 | 112 |
| abstract_inverted_index.We | 37, 60 |
| abstract_inverted_index.by | 25 |
| abstract_inverted_index.in | 39 |
| abstract_inverted_index.is | 130 |
| abstract_inverted_index.of | 4, 42, 56, 78, 98 |
| abstract_inverted_index.on | 137, 151 |
| abstract_inverted_index.to | 66 |
| abstract_inverted_index.we | 118 |
| abstract_inverted_index.(i) | 79 |
| abstract_inverted_index.and | 34, 94, 105 |
| abstract_inverted_index.are | 50, 145 |
| abstract_inverted_index.for | 6, 27, 70 |
| abstract_inverted_index.the | 40, 68, 90, 96, 131, 138 |
| abstract_inverted_index.two | 99 |
| abstract_inverted_index.via | 109 |
| abstract_inverted_index.(ii) | 95 |
| abstract_inverted_index.Over | 111 |
| abstract_inverted_index.RAFT | 139 |
| abstract_inverted_index.This | 75 |
| abstract_inverted_index.best | 132 |
| abstract_inverted_index.data | 20 |
| abstract_inverted_index.each | 28 |
| abstract_inverted_index.from | 89 |
| abstract_inverted_index.hand | 26 |
| abstract_inverted_index.need | 69 |
| abstract_inverted_index.show | 119 |
| abstract_inverted_index.some | 54 |
| abstract_inverted_index.task | 16, 29, 87 |
| abstract_inverted_index.that | 18, 45, 84, 120 |
| abstract_inverted_index.with | 12 |
| abstract_inverted_index.base, | 93 |
| abstract_inverted_index.class | 3, 103 |
| abstract_inverted_index.named | 73 |
| abstract_inverted_index.these | 143 |
| abstract_inverted_index.across | 135 |
| abstract_inverted_index.domain | 32 |
| abstract_inverted_index.method | 65, 134 |
| abstract_inverted_index.models | 11, 49 |
| abstract_inverted_index.module | 83 |
| abstract_inverted_index.prompt | 81 |
| abstract_inverted_index.robust | 52 |
| abstract_inverted_index.simple | 64 |
| abstract_inverted_index.tasks, | 44, 117 |
| abstract_inverted_index.tasks. | 153 |
| abstract_inverted_index.unseen | 152 |
| abstract_inverted_index.AuT-Few | 121, 129 |
| abstract_inverted_index.context | 41 |
| abstract_inverted_index.current | 123 |
| abstract_inverted_index.design. | 59 |
| abstract_inverted_index.prompts | 13, 24, 150 |
| abstract_inverted_index.propose | 62 |
| abstract_inverted_index.ranking | 133 |
| abstract_inverted_index.results | 144 |
| abstract_inverted_index.selects | 85 |
| abstract_inverted_index.towards | 53 |
| abstract_inverted_index.without | 147 |
| abstract_inverted_index.AuT-Few. | 74 |
| abstract_inverted_index.However, | 22 |
| abstract_inverted_index.Notably, | 142 |
| abstract_inverted_index.achieved | 146 |
| abstract_inverted_index.approach | 76 |
| abstract_inverted_index.combines | 9 |
| abstract_inverted_index.commonly | 30 |
| abstract_inverted_index.consists | 77 |
| abstract_inverted_index.datasets | 136 |
| abstract_inverted_index.few-shot | 7, 125, 140 |
| abstract_inverted_index.language | 10, 48 |
| abstract_inverted_index.learning | 8, 126 |
| abstract_inverted_index.methods. | 127 |
| abstract_inverted_index.observe, | 38 |
| abstract_inverted_index.prompts, | 72 |
| abstract_inverted_index.requires | 31 |
| abstract_inverted_index.samples. | 21 |
| abstract_inverted_index.spanning | 114 |
| abstract_inverted_index.suitable | 86 |
| abstract_inverted_index.Moreover, | 128 |
| abstract_inverted_index.datasets, | 113 |
| abstract_inverted_index.designing | 23 |
| abstract_inverted_index.distinct, | 100 |
| abstract_inverted_index.eliminate | 67 |
| abstract_inverted_index.finetuned | 47 |
| abstract_inverted_index.knowledge | 33, 92 |
| abstract_inverted_index.mechanism | 108 |
| abstract_inverted_index.retrieval | 82 |
| abstract_inverted_index.selection | 107 |
| abstract_inverted_index.approaches | 5 |
| abstract_inverted_index.benchmark. | 141 |
| abstract_inverted_index.complement | 19 |
| abstract_inverted_index.dimensions | 55 |
| abstract_inverted_index.generation | 97 |
| abstract_inverted_index.guesswork. | 36 |
| abstract_inverted_index.prompt’s | 58 |
| abstract_inverted_index.remarkably | 51 |
| abstract_inverted_index.successful | 2 |
| abstract_inverted_index.handcrafted | 71, 149 |
| abstract_inverted_index.instruction | 46 |
| abstract_inverted_index.meaningful, | 102 |
| abstract_inverted_index.outperforms | 122 |
| abstract_inverted_index.substantial | 35 |
| abstract_inverted_index.descriptions | 17, 104 |
| abstract_inverted_index.hand-crafted | 15 |
| abstract_inverted_index.instructions | 88 |
| abstract_inverted_index.particularly | 1 |
| abstract_inverted_index.semantically | 101 |
| abstract_inverted_index.subsequently | 61 |
| abstract_inverted_index.task-specific | 148 |
| abstract_inverted_index.classification | 43, 116 |
| abstract_inverted_index.state-of-the-art | 124 |
| abstract_inverted_index.cross-validation. | 110 |
| abstract_inverted_index.instruction-tuning | 91 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8399999737739563 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.69840618 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |