Learning To Retrieve Prompts for In-Context Learning Article Swipe
Ohad Rubin
,
Jonathan Herzig
,
Jonathan Berant
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2022.naacl-main.191
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2022.naacl-main.191
In-context learning is a recent paradigm in natural language understanding, where a large pre-trained language model (LM) observes a test instance and a few training examples as its input, and directly decodes the output without any update to its parameters. However, performance has been shown to strongly depend on the selected training examples (termed prompts). In this work, we propose an efficient method for retrieving prompts for in-context learning using annotated data and an LM. Given an input-output pair, we estimate the probability of the output given the input and a candidate training example as the prompt, and label training examples as positive or negative based on this probability. We then train an efficient dense retriever from this data, which is used to retrieve training examples as prompts at test time. We evaluate our approach on three sequence-to-sequence tasks where language utterances are mapped to meaning representations, and find that it substantially outperforms prior work and multiple baselines across the board.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.18653/v1/2022.naacl-main.191
- https://aclanthology.org/2022.naacl-main.191.pdf
- OA Status
- hybrid
- Cited By
- 283
- References
- 54
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4287891464
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4287891464Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.18653/v1/2022.naacl-main.191Digital Object Identifier
- Title
-
Learning To Retrieve Prompts for In-Context LearningWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-01-01Full publication date if available
- Authors
-
Ohad Rubin, Jonathan Herzig, Jonathan BerantList of authors in order
- Landing page
-
https://doi.org/10.18653/v1/2022.naacl-main.191Publisher landing page
- PDF URL
-
https://aclanthology.org/2022.naacl-main.191.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://aclanthology.org/2022.naacl-main.191.pdfDirect OA link when available
- Concepts
-
Computer science, Context (archaeology), Artificial intelligence, Sequence (biology), Natural language processing, Decodes, Natural language, Language model, Natural language understanding, Training set, Machine learning, Speech recognition, Decoding methods, Algorithm, Genetics, Paleontology, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
283Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 73, 2024: 83, 2023: 118, 2022: 9Per-year citation counts (last 5 years)
- References (count)
-
54Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4287891464 |
|---|---|
| doi | https://doi.org/10.18653/v1/2022.naacl-main.191 |
| ids.doi | https://doi.org/10.18653/v1/2022.naacl-main.191 |
| ids.openalex | https://openalex.org/W4287891464 |
| fwci | 33.3856313 |
| type | article |
| title | Learning To Retrieve Prompts for In-Context Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| 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 | 0.9987999796867371 |
| 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 | 0.9945999979972839 |
| 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/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9904999732971191 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8330437541007996 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2779343474 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6612021923065186 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[1].display_name | Context (archaeology) |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.580902636051178 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C2778112365 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5703535079956055 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3511065 |
| concepts[3].display_name | Sequence (biology) |
| concepts[4].id | https://openalex.org/C204321447 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5186052322387695 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[4].display_name | Natural language processing |
| concepts[5].id | https://openalex.org/C2778858076 |
| concepts[5].level | 3 |
| concepts[5].score | 0.4891801178455353 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q5249539 |
| concepts[5].display_name | Decodes |
| concepts[6].id | https://openalex.org/C195324797 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4566672146320343 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q33742 |
| concepts[6].display_name | Natural language |
| concepts[7].id | https://openalex.org/C137293760 |
| concepts[7].level | 2 |
| concepts[7].score | 0.43081676959991455 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[7].display_name | Language model |
| concepts[8].id | https://openalex.org/C2779439875 |
| concepts[8].level | 3 |
| concepts[8].score | 0.42617395520210266 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q1078276 |
| concepts[8].display_name | Natural language understanding |
| concepts[9].id | https://openalex.org/C51632099 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4189378619194031 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q3985153 |
| concepts[9].display_name | Training set |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3731371760368347 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C28490314 |
| concepts[11].level | 1 |
| concepts[11].score | 0.3223913908004761 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[11].display_name | Speech recognition |
| concepts[12].id | https://openalex.org/C57273362 |
| concepts[12].level | 2 |
| concepts[12].score | 0.1265038251876831 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q576722 |
| concepts[12].display_name | Decoding methods |
| concepts[13].id | https://openalex.org/C11413529 |
| concepts[13].level | 1 |
| concepts[13].score | 0.1194983720779419 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[13].display_name | Algorithm |
| concepts[14].id | https://openalex.org/C54355233 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7162 |
| concepts[14].display_name | Genetics |
| concepts[15].id | https://openalex.org/C151730666 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[15].display_name | Paleontology |
| concepts[16].id | https://openalex.org/C86803240 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[16].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8330437541007996 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/context |
| keywords[1].score | 0.6612021923065186 |
| keywords[1].display_name | Context (archaeology) |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.580902636051178 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/sequence |
| keywords[3].score | 0.5703535079956055 |
| keywords[3].display_name | Sequence (biology) |
| keywords[4].id | https://openalex.org/keywords/natural-language-processing |
| keywords[4].score | 0.5186052322387695 |
| keywords[4].display_name | Natural language processing |
| keywords[5].id | https://openalex.org/keywords/decodes |
| keywords[5].score | 0.4891801178455353 |
| keywords[5].display_name | Decodes |
| keywords[6].id | https://openalex.org/keywords/natural-language |
| keywords[6].score | 0.4566672146320343 |
| keywords[6].display_name | Natural language |
| keywords[7].id | https://openalex.org/keywords/language-model |
| keywords[7].score | 0.43081676959991455 |
| keywords[7].display_name | Language model |
| keywords[8].id | https://openalex.org/keywords/natural-language-understanding |
| keywords[8].score | 0.42617395520210266 |
| keywords[8].display_name | Natural language understanding |
| keywords[9].id | https://openalex.org/keywords/training-set |
| keywords[9].score | 0.4189378619194031 |
| keywords[9].display_name | Training set |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.3731371760368347 |
| keywords[10].display_name | Machine learning |
| keywords[11].id | https://openalex.org/keywords/speech-recognition |
| keywords[11].score | 0.3223913908004761 |
| keywords[11].display_name | Speech recognition |
| keywords[12].id | https://openalex.org/keywords/decoding-methods |
| keywords[12].score | 0.1265038251876831 |
| keywords[12].display_name | Decoding methods |
| keywords[13].id | https://openalex.org/keywords/algorithm |
| keywords[13].score | 0.1194983720779419 |
| keywords[13].display_name | Algorithm |
| language | en |
| locations[0].id | doi:10.18653/v1/2022.naacl-main.191 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4363608774 |
| locations[0].source.issn | |
| locations[0].source.type | conference |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://aclanthology.org/2022.naacl-main.191.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 | Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| locations[0].landing_page_url | https://doi.org/10.18653/v1/2022.naacl-main.191 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5077371707 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Ohad Rubin |
| authorships[0].countries | IL |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I16391192 |
| authorships[0].affiliations[0].raw_affiliation_string | The Blavatnik School of Computer Science, Tel Aviv University |
| authorships[0].institutions[0].id | https://openalex.org/I16391192 |
| authorships[0].institutions[0].ror | https://ror.org/04mhzgx49 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I16391192 |
| authorships[0].institutions[0].country_code | IL |
| authorships[0].institutions[0].display_name | Tel Aviv University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ohad Rubin |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | The Blavatnik School of Computer Science, Tel Aviv University |
| authorships[1].author.id | https://openalex.org/A5071893787 |
| authorships[1].author.orcid | https://orcid.org/0009-0000-7227-6557 |
| authorships[1].author.display_name | Jonathan Herzig |
| authorships[1].countries | IL |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I16391192 |
| authorships[1].affiliations[0].raw_affiliation_string | The Blavatnik School of Computer Science, Tel Aviv University |
| authorships[1].institutions[0].id | https://openalex.org/I16391192 |
| authorships[1].institutions[0].ror | https://ror.org/04mhzgx49 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I16391192 |
| authorships[1].institutions[0].country_code | IL |
| authorships[1].institutions[0].display_name | Tel Aviv University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jonathan Herzig |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | The Blavatnik School of Computer Science, Tel Aviv University |
| authorships[2].author.id | https://openalex.org/A5045872048 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Jonathan Berant |
| authorships[2].countries | IL |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I16391192 |
| authorships[2].affiliations[0].raw_affiliation_string | The Blavatnik School of Computer Science, Tel Aviv University |
| authorships[2].institutions[0].id | https://openalex.org/I16391192 |
| authorships[2].institutions[0].ror | https://ror.org/04mhzgx49 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I16391192 |
| authorships[2].institutions[0].country_code | IL |
| authorships[2].institutions[0].display_name | Tel Aviv University |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Jonathan Berant |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | The Blavatnik School of Computer Science, Tel Aviv 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/2022.naacl-main.191.pdf |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Learning To Retrieve Prompts for In-Context Learning |
| 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 | 0.9987999796867371 |
| 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/W2977842567, https://openalex.org/W4226226396, https://openalex.org/W1542956019, https://openalex.org/W4308854837, https://openalex.org/W3046207468, https://openalex.org/W2783089240, https://openalex.org/W4287548963, https://openalex.org/W3118032223, https://openalex.org/W69953359, https://openalex.org/W3212368093 |
| cited_by_count | 283 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 73 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 83 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 118 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 9 |
| locations_count | 1 |
| best_oa_location.id | doi:10.18653/v1/2022.naacl-main.191 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4363608774 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://aclanthology.org/2022.naacl-main.191.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 | Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| best_oa_location.landing_page_url | https://doi.org/10.18653/v1/2022.naacl-main.191 |
| primary_location.id | doi:10.18653/v1/2022.naacl-main.191 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4363608774 |
| primary_location.source.issn | |
| primary_location.source.type | conference |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://aclanthology.org/2022.naacl-main.191.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 | Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| primary_location.landing_page_url | https://doi.org/10.18653/v1/2022.naacl-main.191 |
| publication_date | 2022-01-01 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W3098267758, https://openalex.org/W3118781290, https://openalex.org/W4226082499, https://openalex.org/W3034439313, https://openalex.org/W4299585995, https://openalex.org/W4297801719, https://openalex.org/W3152729555, https://openalex.org/W4287026929, https://openalex.org/W4385567149, https://openalex.org/W3154903254, https://openalex.org/W1522301498, https://openalex.org/W3168659546, https://openalex.org/W3133702157, https://openalex.org/W4221155916, https://openalex.org/W3152740956, https://openalex.org/W4288089799, https://openalex.org/W3177813494, https://openalex.org/W4286907499, https://openalex.org/W3099700870, https://openalex.org/W3027879771, https://openalex.org/W2893167765, https://openalex.org/W2611029872, https://openalex.org/W4306754402, https://openalex.org/W4285122897, https://openalex.org/W2970641574, https://openalex.org/W3016828850, https://openalex.org/W2157444450, https://openalex.org/W3172943453, https://openalex.org/W3153427360, https://openalex.org/W4226146865, https://openalex.org/W3168875417, https://openalex.org/W4205857304, https://openalex.org/W3156012351, https://openalex.org/W2963341956, https://openalex.org/W3092185277, https://openalex.org/W4288087322, https://openalex.org/W4308900200, https://openalex.org/W4287649493, https://openalex.org/W3212496002, https://openalex.org/W2962985038, https://openalex.org/W4292779060, https://openalex.org/W3034671305, https://openalex.org/W4286769130, https://openalex.org/W2951434086, https://openalex.org/W3166846774, https://openalex.org/W4252076394, https://openalex.org/W2970476646, https://openalex.org/W3105388824, https://openalex.org/W2160642098, https://openalex.org/W3206547074, https://openalex.org/W4200634402, https://openalex.org/W3166986030, https://openalex.org/W3156414406, https://openalex.org/W3174770825 |
| referenced_works_count | 54 |
| abstract_inverted_index.a | 3, 11, 18, 22, 90 |
| abstract_inverted_index.In | 55 |
| abstract_inverted_index.We | 109, 131 |
| abstract_inverted_index.an | 60, 73, 76, 112 |
| abstract_inverted_index.as | 26, 94, 101, 126 |
| abstract_inverted_index.at | 128 |
| abstract_inverted_index.in | 6 |
| abstract_inverted_index.is | 2, 120 |
| abstract_inverted_index.it | 150 |
| abstract_inverted_index.of | 83 |
| abstract_inverted_index.on | 48, 106, 135 |
| abstract_inverted_index.or | 103 |
| abstract_inverted_index.to | 37, 45, 122, 144 |
| abstract_inverted_index.we | 58, 79 |
| abstract_inverted_index.LM. | 74 |
| abstract_inverted_index.and | 21, 29, 72, 89, 97, 147, 155 |
| abstract_inverted_index.any | 35 |
| abstract_inverted_index.are | 142 |
| abstract_inverted_index.few | 23 |
| abstract_inverted_index.for | 63, 66 |
| abstract_inverted_index.has | 42 |
| abstract_inverted_index.its | 27, 38 |
| abstract_inverted_index.our | 133 |
| abstract_inverted_index.the | 32, 49, 81, 84, 87, 95, 159 |
| abstract_inverted_index.(LM) | 16 |
| abstract_inverted_index.been | 43 |
| abstract_inverted_index.data | 71 |
| abstract_inverted_index.find | 148 |
| abstract_inverted_index.from | 116 |
| abstract_inverted_index.test | 19, 129 |
| abstract_inverted_index.that | 149 |
| abstract_inverted_index.then | 110 |
| abstract_inverted_index.this | 56, 107, 117 |
| abstract_inverted_index.used | 121 |
| abstract_inverted_index.work | 154 |
| abstract_inverted_index.Given | 75 |
| abstract_inverted_index.based | 105 |
| abstract_inverted_index.data, | 118 |
| abstract_inverted_index.dense | 114 |
| abstract_inverted_index.given | 86 |
| abstract_inverted_index.input | 88 |
| abstract_inverted_index.label | 98 |
| abstract_inverted_index.large | 12 |
| abstract_inverted_index.model | 15 |
| abstract_inverted_index.pair, | 78 |
| abstract_inverted_index.prior | 153 |
| abstract_inverted_index.shown | 44 |
| abstract_inverted_index.tasks | 138 |
| abstract_inverted_index.three | 136 |
| abstract_inverted_index.time. | 130 |
| abstract_inverted_index.train | 111 |
| abstract_inverted_index.using | 69 |
| abstract_inverted_index.where | 10, 139 |
| abstract_inverted_index.which | 119 |
| abstract_inverted_index.work, | 57 |
| abstract_inverted_index.across | 158 |
| abstract_inverted_index.board. | 160 |
| abstract_inverted_index.depend | 47 |
| abstract_inverted_index.input, | 28 |
| abstract_inverted_index.mapped | 143 |
| abstract_inverted_index.method | 62 |
| abstract_inverted_index.output | 33, 85 |
| abstract_inverted_index.recent | 4 |
| abstract_inverted_index.update | 36 |
| abstract_inverted_index.(termed | 53 |
| abstract_inverted_index.decodes | 31 |
| abstract_inverted_index.example | 93 |
| abstract_inverted_index.meaning | 145 |
| abstract_inverted_index.natural | 7 |
| abstract_inverted_index.prompt, | 96 |
| abstract_inverted_index.prompts | 65, 127 |
| abstract_inverted_index.propose | 59 |
| abstract_inverted_index.without | 34 |
| abstract_inverted_index.However, | 40 |
| abstract_inverted_index.approach | 134 |
| abstract_inverted_index.directly | 30 |
| abstract_inverted_index.estimate | 80 |
| abstract_inverted_index.evaluate | 132 |
| abstract_inverted_index.examples | 25, 52, 100, 125 |
| abstract_inverted_index.instance | 20 |
| abstract_inverted_index.language | 8, 14, 140 |
| abstract_inverted_index.learning | 1, 68 |
| abstract_inverted_index.multiple | 156 |
| abstract_inverted_index.negative | 104 |
| abstract_inverted_index.observes | 17 |
| abstract_inverted_index.paradigm | 5 |
| abstract_inverted_index.positive | 102 |
| abstract_inverted_index.retrieve | 123 |
| abstract_inverted_index.selected | 50 |
| abstract_inverted_index.strongly | 46 |
| abstract_inverted_index.training | 24, 51, 92, 99, 124 |
| abstract_inverted_index.annotated | 70 |
| abstract_inverted_index.baselines | 157 |
| abstract_inverted_index.candidate | 91 |
| abstract_inverted_index.efficient | 61, 113 |
| abstract_inverted_index.prompts). | 54 |
| abstract_inverted_index.retriever | 115 |
| abstract_inverted_index.In-context | 0 |
| abstract_inverted_index.in-context | 67 |
| abstract_inverted_index.retrieving | 64 |
| abstract_inverted_index.utterances | 141 |
| abstract_inverted_index.outperforms | 152 |
| abstract_inverted_index.parameters. | 39 |
| abstract_inverted_index.performance | 41 |
| abstract_inverted_index.pre-trained | 13 |
| abstract_inverted_index.probability | 82 |
| abstract_inverted_index.input-output | 77 |
| abstract_inverted_index.probability. | 108 |
| abstract_inverted_index.substantially | 151 |
| abstract_inverted_index.understanding, | 9 |
| abstract_inverted_index.representations, | 146 |
| abstract_inverted_index.sequence-to-sequence | 137 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 99 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8100000023841858 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.99859868 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |