Promptagator: Few-shot Dense Retrieval From 8 Examples Article Swipe
Zhuyun Dai
,
Vincent Y. Zhao
,
Ji Ma
,
Yi Luan
,
Jianmo Ni
,
Jing Lü
,
Anton Bakalov
,
Kelvin Guu
,
Keith Hall
,
Ming‐Wei Chang
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2209.11755
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2209.11755
Much recent research on information retrieval has focused on how to transfer from one task (typically with abundant supervised data) to various other tasks where supervision is limited, with the implicit assumption that it is possible to generalize from one task to all the rest. However, this overlooks the fact that there are many diverse and unique retrieval tasks, each targeting different search intents, queries, and search domains. In this paper, we suggest to work on Few-shot Dense Retrieval, a setting where each task comes with a short description and a few examples. To amplify the power of a few examples, we propose Prompt-base Query Generation for Retriever (Promptagator), which leverages large language models (LLM) as a few-shot query generator, and creates task-specific retrievers based on the generated data. Powered by LLM's generalization ability, Promptagator makes it possible to create task-specific end-to-end retrievers solely based on a few examples {without} using Natural Questions or MS MARCO to train %question generators or dual encoders. Surprisingly, LLM prompting with no more than 8 examples allows dual encoders to outperform heavily engineered models trained on MS MARCO like ColBERT v2 by more than 1.2 nDCG on average on 11 retrieval sets. Further training standard-size re-rankers using the same generated data yields another 5.0 point nDCG improvement. Our studies determine that query generation can be far more effective than previously observed, especially when a small amount of task-specific knowledge is given.
Related Topics
Concepts
Computer science
Task (project management)
Encoder
Information retrieval
Learning to rank
Artificial intelligence
Question answering
Generalization
Dual (grammatical number)
Point (geometry)
Machine learning
Ranking (information retrieval)
Mathematical analysis
Geometry
Management
Mathematics
Literature
Economics
Art
Operating system
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2209.11755
- https://arxiv.org/pdf/2209.11755
- OA Status
- green
- Cited By
- 46
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4297162632
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4297162632Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2209.11755Digital Object Identifier
- Title
-
Promptagator: Few-shot Dense Retrieval From 8 ExamplesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-09-23Full publication date if available
- Authors
-
Zhuyun Dai, Vincent Y. Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lü, Anton Bakalov, Kelvin Guu, Keith Hall, Ming‐Wei ChangList of authors in order
- Landing page
-
https://arxiv.org/abs/2209.11755Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2209.11755Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2209.11755Direct OA link when available
- Concepts
-
Computer science, Task (project management), Encoder, Information retrieval, Learning to rank, Artificial intelligence, Question answering, Generalization, Dual (grammatical number), Point (geometry), Machine learning, Ranking (information retrieval), Mathematical analysis, Geometry, Management, Mathematics, Literature, Economics, Art, Operating systemTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
46Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 3, 2024: 9, 2023: 34Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4297162632 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2209.11755 |
| ids.doi | https://doi.org/10.48550/arxiv.2209.11755 |
| ids.openalex | https://openalex.org/W4297162632 |
| fwci | |
| type | preprint |
| title | Promptagator: Few-shot Dense Retrieval From 8 Examples |
| 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 | 0.9994000196456909 |
| 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 | 0.9965000152587891 |
| 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 | 0.9914000034332275 |
| 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 | 0.8440678119659424 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2780451532 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6985389590263367 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[1].display_name | Task (project management) |
| concepts[2].id | https://openalex.org/C118505674 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6234008073806763 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[2].display_name | Encoder |
| concepts[3].id | https://openalex.org/C23123220 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5305115580558777 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[3].display_name | Information retrieval |
| concepts[4].id | https://openalex.org/C86037889 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5280759334564209 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q4330127 |
| concepts[4].display_name | Learning to rank |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5006136894226074 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C44291984 |
| concepts[6].level | 2 |
| concepts[6].score | 0.46778404712677 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1074173 |
| concepts[6].display_name | Question answering |
| concepts[7].id | https://openalex.org/C177148314 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4584827125072479 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q170084 |
| concepts[7].display_name | Generalization |
| concepts[8].id | https://openalex.org/C2780980858 |
| concepts[8].level | 2 |
| concepts[8].score | 0.45027297735214233 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q110022 |
| concepts[8].display_name | Dual (grammatical number) |
| concepts[9].id | https://openalex.org/C28719098 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4176555573940277 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q44946 |
| concepts[9].display_name | Point (geometry) |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3571857810020447 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C189430467 |
| concepts[11].level | 2 |
| concepts[11].score | 0.34406304359436035 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7293293 |
| concepts[11].display_name | Ranking (information retrieval) |
| concepts[12].id | https://openalex.org/C134306372 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[12].display_name | Mathematical analysis |
| concepts[13].id | https://openalex.org/C2524010 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[13].display_name | Geometry |
| concepts[14].id | https://openalex.org/C187736073 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[14].display_name | Management |
| concepts[15].id | https://openalex.org/C33923547 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[15].display_name | Mathematics |
| concepts[16].id | https://openalex.org/C124952713 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q8242 |
| concepts[16].display_name | Literature |
| concepts[17].id | https://openalex.org/C162324750 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[17].display_name | Economics |
| concepts[18].id | https://openalex.org/C142362112 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q735 |
| concepts[18].display_name | Art |
| concepts[19].id | https://openalex.org/C111919701 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[19].display_name | Operating system |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8440678119659424 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/task |
| keywords[1].score | 0.6985389590263367 |
| keywords[1].display_name | Task (project management) |
| keywords[2].id | https://openalex.org/keywords/encoder |
| keywords[2].score | 0.6234008073806763 |
| keywords[2].display_name | Encoder |
| keywords[3].id | https://openalex.org/keywords/information-retrieval |
| keywords[3].score | 0.5305115580558777 |
| keywords[3].display_name | Information retrieval |
| keywords[4].id | https://openalex.org/keywords/learning-to-rank |
| keywords[4].score | 0.5280759334564209 |
| keywords[4].display_name | Learning to rank |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.5006136894226074 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/question-answering |
| keywords[6].score | 0.46778404712677 |
| keywords[6].display_name | Question answering |
| keywords[7].id | https://openalex.org/keywords/generalization |
| keywords[7].score | 0.4584827125072479 |
| keywords[7].display_name | Generalization |
| keywords[8].id | https://openalex.org/keywords/dual |
| keywords[8].score | 0.45027297735214233 |
| keywords[8].display_name | Dual (grammatical number) |
| keywords[9].id | https://openalex.org/keywords/point |
| keywords[9].score | 0.4176555573940277 |
| keywords[9].display_name | Point (geometry) |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.3571857810020447 |
| keywords[10].display_name | Machine learning |
| keywords[11].id | https://openalex.org/keywords/ranking |
| keywords[11].score | 0.34406304359436035 |
| keywords[11].display_name | Ranking (information retrieval) |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2209.11755 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2209.11755 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2209.11755 |
| locations[1].id | doi:10.48550/arxiv.2209.11755 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2209.11755 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5062633736 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Zhuyun Dai |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Dai, Zhuyun |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5045803583 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Vincent Y. Zhao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhao, Vincent Y. |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100460563 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2181-5121 |
| authorships[2].author.display_name | Ji Ma |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ma, Ji |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5009136371 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5914-9622 |
| authorships[3].author.display_name | Yi Luan |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Luan, Yi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5077817759 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-6863-8073 |
| authorships[4].author.display_name | Jianmo Ni |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ni, Jianmo |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100460378 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-9163-8795 |
| authorships[5].author.display_name | Jing Lü |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Lu, Jing |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5072205226 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Anton Bakalov |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Bakalov, Anton |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5076669462 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Kelvin Guu |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Guu, Kelvin |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5013958949 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-0977-6572 |
| authorships[8].author.display_name | Keith Hall |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Hall, Keith B. |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5076904467 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-0137-8895 |
| authorships[9].author.display_name | Ming‐Wei Chang |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Chang, Ming-Wei |
| authorships[9].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2209.11755 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Promptagator: Few-shot Dense Retrieval From 8 Examples |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| 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 | 0.9994000196456909 |
| 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/W3127142483, https://openalex.org/W4385565564, https://openalex.org/W2898073868, https://openalex.org/W2138488530, https://openalex.org/W4390446658, https://openalex.org/W2971071571, https://openalex.org/W2798835721, https://openalex.org/W2387658907, https://openalex.org/W25098770, https://openalex.org/W2385796165 |
| cited_by_count | 46 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 3 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 9 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 34 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2209.11755 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| 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 | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2209.11755 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2209.11755 |
| primary_location.id | pmh:oai:arXiv.org:2209.11755 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2209.11755 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2209.11755 |
| publication_date | 2022-09-23 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.8 | 170 |
| abstract_inverted_index.a | 79, 86, 90, 98, 116, 146, 229 |
| abstract_inverted_index.11 | 195 |
| abstract_inverted_index.In | 68 |
| abstract_inverted_index.MS | 154, 182 |
| abstract_inverted_index.To | 93 |
| abstract_inverted_index.as | 115 |
| abstract_inverted_index.be | 220 |
| abstract_inverted_index.by | 130, 187 |
| abstract_inverted_index.is | 26, 34, 235 |
| abstract_inverted_index.it | 33, 136 |
| abstract_inverted_index.no | 167 |
| abstract_inverted_index.of | 97, 232 |
| abstract_inverted_index.on | 3, 8, 75, 125, 145, 181, 192, 194 |
| abstract_inverted_index.or | 153, 160 |
| abstract_inverted_index.to | 10, 20, 36, 41, 73, 138, 156, 175 |
| abstract_inverted_index.v2 | 186 |
| abstract_inverted_index.we | 71, 101 |
| abstract_inverted_index.1.2 | 190 |
| abstract_inverted_index.5.0 | 209 |
| abstract_inverted_index.LLM | 164 |
| abstract_inverted_index.Our | 213 |
| abstract_inverted_index.all | 42 |
| abstract_inverted_index.and | 55, 65, 89, 120 |
| abstract_inverted_index.are | 52 |
| abstract_inverted_index.can | 219 |
| abstract_inverted_index.far | 221 |
| abstract_inverted_index.few | 91, 99, 147 |
| abstract_inverted_index.for | 106 |
| abstract_inverted_index.has | 6 |
| abstract_inverted_index.how | 9 |
| abstract_inverted_index.one | 13, 39 |
| abstract_inverted_index.the | 29, 43, 48, 95, 126, 203 |
| abstract_inverted_index.Much | 0 |
| abstract_inverted_index.data | 206 |
| abstract_inverted_index.dual | 161, 173 |
| abstract_inverted_index.each | 59, 82 |
| abstract_inverted_index.fact | 49 |
| abstract_inverted_index.from | 12, 38 |
| abstract_inverted_index.like | 184 |
| abstract_inverted_index.many | 53 |
| abstract_inverted_index.more | 168, 188, 222 |
| abstract_inverted_index.nDCG | 191, 211 |
| abstract_inverted_index.same | 204 |
| abstract_inverted_index.task | 14, 40, 83 |
| abstract_inverted_index.than | 169, 189, 224 |
| abstract_inverted_index.that | 32, 50, 216 |
| abstract_inverted_index.this | 46, 69 |
| abstract_inverted_index.when | 228 |
| abstract_inverted_index.with | 16, 28, 85, 166 |
| abstract_inverted_index.work | 74 |
| abstract_inverted_index.(LLM) | 114 |
| abstract_inverted_index.Dense | 77 |
| abstract_inverted_index.LLM's | 131 |
| abstract_inverted_index.MARCO | 155, 183 |
| abstract_inverted_index.Query | 104 |
| abstract_inverted_index.based | 124, 144 |
| abstract_inverted_index.comes | 84 |
| abstract_inverted_index.data) | 19 |
| abstract_inverted_index.data. | 128 |
| abstract_inverted_index.large | 111 |
| abstract_inverted_index.makes | 135 |
| abstract_inverted_index.other | 22 |
| abstract_inverted_index.point | 210 |
| abstract_inverted_index.power | 96 |
| abstract_inverted_index.query | 118, 217 |
| abstract_inverted_index.rest. | 44 |
| abstract_inverted_index.sets. | 197 |
| abstract_inverted_index.short | 87 |
| abstract_inverted_index.small | 230 |
| abstract_inverted_index.tasks | 23 |
| abstract_inverted_index.there | 51 |
| abstract_inverted_index.train | 157 |
| abstract_inverted_index.using | 150, 202 |
| abstract_inverted_index.where | 24, 81 |
| abstract_inverted_index.which | 109 |
| abstract_inverted_index.allows | 172 |
| abstract_inverted_index.amount | 231 |
| abstract_inverted_index.create | 139 |
| abstract_inverted_index.given. | 236 |
| abstract_inverted_index.models | 113, 179 |
| abstract_inverted_index.paper, | 70 |
| abstract_inverted_index.recent | 1 |
| abstract_inverted_index.search | 62, 66 |
| abstract_inverted_index.solely | 143 |
| abstract_inverted_index.tasks, | 58 |
| abstract_inverted_index.unique | 56 |
| abstract_inverted_index.yields | 207 |
| abstract_inverted_index.ColBERT | 185 |
| abstract_inverted_index.Further | 198 |
| abstract_inverted_index.Natural | 151 |
| abstract_inverted_index.Powered | 129 |
| abstract_inverted_index.amplify | 94 |
| abstract_inverted_index.another | 208 |
| abstract_inverted_index.average | 193 |
| abstract_inverted_index.creates | 121 |
| abstract_inverted_index.diverse | 54 |
| abstract_inverted_index.focused | 7 |
| abstract_inverted_index.heavily | 177 |
| abstract_inverted_index.propose | 102 |
| abstract_inverted_index.setting | 80 |
| abstract_inverted_index.studies | 214 |
| abstract_inverted_index.suggest | 72 |
| abstract_inverted_index.trained | 180 |
| abstract_inverted_index.various | 21 |
| abstract_inverted_index.Few-shot | 76 |
| abstract_inverted_index.However, | 45 |
| abstract_inverted_index.ability, | 133 |
| abstract_inverted_index.abundant | 17 |
| abstract_inverted_index.domains. | 67 |
| abstract_inverted_index.encoders | 174 |
| abstract_inverted_index.examples | 148, 171 |
| abstract_inverted_index.few-shot | 117 |
| abstract_inverted_index.implicit | 30 |
| abstract_inverted_index.intents, | 63 |
| abstract_inverted_index.language | 112 |
| abstract_inverted_index.limited, | 27 |
| abstract_inverted_index.possible | 35, 137 |
| abstract_inverted_index.queries, | 64 |
| abstract_inverted_index.research | 2 |
| abstract_inverted_index.training | 199 |
| abstract_inverted_index.transfer | 11 |
| abstract_inverted_index.%question | 158 |
| abstract_inverted_index.Questions | 152 |
| abstract_inverted_index.Retriever | 107 |
| abstract_inverted_index.determine | 215 |
| abstract_inverted_index.different | 61 |
| abstract_inverted_index.effective | 223 |
| abstract_inverted_index.encoders. | 162 |
| abstract_inverted_index.examples, | 100 |
| abstract_inverted_index.examples. | 92 |
| abstract_inverted_index.generated | 127, 205 |
| abstract_inverted_index.knowledge | 234 |
| abstract_inverted_index.leverages | 110 |
| abstract_inverted_index.observed, | 226 |
| abstract_inverted_index.overlooks | 47 |
| abstract_inverted_index.prompting | 165 |
| abstract_inverted_index.retrieval | 5, 57, 196 |
| abstract_inverted_index.targeting | 60 |
| abstract_inverted_index.{without} | 149 |
| abstract_inverted_index.(typically | 15 |
| abstract_inverted_index.Generation | 105 |
| abstract_inverted_index.Retrieval, | 78 |
| abstract_inverted_index.assumption | 31 |
| abstract_inverted_index.end-to-end | 141 |
| abstract_inverted_index.engineered | 178 |
| abstract_inverted_index.especially | 227 |
| abstract_inverted_index.generalize | 37 |
| abstract_inverted_index.generation | 218 |
| abstract_inverted_index.generator, | 119 |
| abstract_inverted_index.generators | 159 |
| abstract_inverted_index.outperform | 176 |
| abstract_inverted_index.previously | 225 |
| abstract_inverted_index.re-rankers | 201 |
| abstract_inverted_index.retrievers | 123, 142 |
| abstract_inverted_index.supervised | 18 |
| abstract_inverted_index.Prompt-base | 103 |
| abstract_inverted_index.description | 88 |
| abstract_inverted_index.information | 4 |
| abstract_inverted_index.supervision | 25 |
| abstract_inverted_index.Promptagator | 134 |
| abstract_inverted_index.improvement. | 212 |
| abstract_inverted_index.Surprisingly, | 163 |
| abstract_inverted_index.standard-size | 200 |
| abstract_inverted_index.task-specific | 122, 140, 233 |
| abstract_inverted_index.generalization | 132 |
| abstract_inverted_index.(Promptagator), | 108 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| citation_normalized_percentile |