FsPONER: Few-Shot Prompt Optimization for Named Entity Recognition in Domain-Specific Scenarios Article Swipe
Yongjian Tang
,
Rakebul Hasan
,
Thomas A. Runkler
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.3233/faia240936
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.3233/faia240936
Large Language Models (LLMs) have provided a new pathway for Named Entity Recognition (NER) tasks. Compared with fine-tuning, LLM-powered prompting methods avoid the need for training, conserve substantial computational resources, and rely on minimal annotated data. Previous studies have achieved comparable performance to fully supervised BERT-based fine-tuning approaches on general NER benchmarks. However, none of the previous approaches has investigated the efficiency of LLM-based few-shot learning in domain-specific scenarios. To address this gap, we introduce FsPONER, a novel approach for optimizing few-shot prompts, and evaluate its performance on domain-specific NER datasets, with a focus on industrial manufacturing and maintenance, while using multiple LLMs – GPT-4-32K, GPT-3.5-Turbo, LLaMA 2-chat, and Vicuna. FsPONER consists of three few-shot selection methods based on random sampling, TF-IDF vectors, and a combination of both. We compare these methods with a general-purpose GPT-NER method as the number of few-shot examples increases and evaluate their optimal NER performance against fine-tuned BERT and LLaMA 2-chat. In the considered real-world scenarios with data scarcity, FsPONER with TF-IDF surpasses fine-tuned models by approximately 10% in F1 score.
Related Topics
Concepts
Metadata
- Type
- book-chapter
- Language
- en
- Landing Page
- https://doi.org/10.3233/faia240936
- https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240936
- OA Status
- hybrid
- Cited By
- 3
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403487242
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403487242Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.3233/faia240936Digital Object Identifier
- Title
-
FsPONER: Few-Shot Prompt Optimization for Named Entity Recognition in Domain-Specific ScenariosWork title
- Type
-
book-chapterOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-10-16Full publication date if available
- Authors
-
Yongjian Tang, Rakebul Hasan, Thomas A. RunklerList of authors in order
- Landing page
-
https://doi.org/10.3233/faia240936Publisher landing page
- PDF URL
-
https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240936Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240936Direct OA link when available
- Concepts
-
Shot (pellet), Computer science, Domain (mathematical analysis), Artificial intelligence, Natural language processing, Named-entity recognition, Mathematics, Engineering, Task (project management), Chemistry, Systems engineering, Organic chemistry, Mathematical analysisTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 3Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403487242 |
|---|---|
| doi | https://doi.org/10.3233/faia240936 |
| ids.doi | https://doi.org/10.3233/faia240936 |
| ids.openalex | https://openalex.org/W4403487242 |
| fwci | 3.77994691 |
| type | book-chapter |
| title | FsPONER: Few-Shot Prompt Optimization for Named Entity Recognition in Domain-Specific Scenarios |
| 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 | 0.9995999932289124 |
| 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 | 0.9976999759674072 |
| 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/T11719 |
| topics[2].field.id | https://openalex.org/fields/18 |
| topics[2].field.display_name | Decision Sciences |
| topics[2].score | 0.9405999779701233 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1803 |
| topics[2].subfield.display_name | Management Science and Operations Research |
| topics[2].display_name | Data Quality and Management |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2778344882 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7399547696113586 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q278938 |
| concepts[0].display_name | Shot (pellet) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6131747961044312 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C36503486 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5811190009117126 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11235244 |
| concepts[2].display_name | Domain (mathematical analysis) |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5105222463607788 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C204321447 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4323990046977997 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[4].display_name | Natural language processing |
| concepts[5].id | https://openalex.org/C2779135771 |
| concepts[5].level | 3 |
| concepts[5].score | 0.41269540786743164 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q403574 |
| concepts[5].display_name | Named-entity recognition |
| concepts[6].id | https://openalex.org/C33923547 |
| concepts[6].level | 0 |
| concepts[6].score | 0.1469908356666565 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[6].display_name | Mathematics |
| concepts[7].id | https://openalex.org/C127413603 |
| concepts[7].level | 0 |
| concepts[7].score | 0.11075422167778015 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[7].display_name | Engineering |
| concepts[8].id | https://openalex.org/C2780451532 |
| concepts[8].level | 2 |
| concepts[8].score | 0.08473795652389526 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[8].display_name | Task (project management) |
| concepts[9].id | https://openalex.org/C185592680 |
| concepts[9].level | 0 |
| concepts[9].score | 0.05276155471801758 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[9].display_name | Chemistry |
| concepts[10].id | https://openalex.org/C201995342 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[10].display_name | Systems engineering |
| concepts[11].id | https://openalex.org/C178790620 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11351 |
| concepts[11].display_name | Organic chemistry |
| 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 |
| keywords[0].id | https://openalex.org/keywords/shot |
| keywords[0].score | 0.7399547696113586 |
| keywords[0].display_name | Shot (pellet) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6131747961044312 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/domain |
| keywords[2].score | 0.5811190009117126 |
| keywords[2].display_name | Domain (mathematical analysis) |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5105222463607788 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/natural-language-processing |
| keywords[4].score | 0.4323990046977997 |
| keywords[4].display_name | Natural language processing |
| keywords[5].id | https://openalex.org/keywords/named-entity-recognition |
| keywords[5].score | 0.41269540786743164 |
| keywords[5].display_name | Named-entity recognition |
| keywords[6].id | https://openalex.org/keywords/mathematics |
| keywords[6].score | 0.1469908356666565 |
| keywords[6].display_name | Mathematics |
| keywords[7].id | https://openalex.org/keywords/engineering |
| keywords[7].score | 0.11075422167778015 |
| keywords[7].display_name | Engineering |
| keywords[8].id | https://openalex.org/keywords/task |
| keywords[8].score | 0.08473795652389526 |
| keywords[8].display_name | Task (project management) |
| keywords[9].id | https://openalex.org/keywords/chemistry |
| keywords[9].score | 0.05276155471801758 |
| keywords[9].display_name | Chemistry |
| language | en |
| locations[0].id | doi:10.3233/faia240936 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210201731 |
| locations[0].source.issn | 0922-6389, 1879-8314 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 0922-6389 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Frontiers in artificial intelligence and applications |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | cc-by-nc |
| locations[0].pdf_url | https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240936 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | book-chapter |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Frontiers in Artificial Intelligence and Applications |
| locations[0].landing_page_url | https://doi.org/10.3233/faia240936 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5050053046 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-2223-6420 |
| authorships[0].author.display_name | Yongjian Tang |
| authorships[0].countries | DE |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I62916508 |
| authorships[0].affiliations[0].raw_affiliation_string | Technical University of Munich, Germany |
| authorships[0].affiliations[1].institution_ids | https://openalex.org/I1325886976 |
| authorships[0].affiliations[1].raw_affiliation_string | Siemens AG, Munich, Germany |
| authorships[0].institutions[0].id | https://openalex.org/I1325886976 |
| authorships[0].institutions[0].ror | https://ror.org/059mq0909 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I1325886976 |
| authorships[0].institutions[0].country_code | DE |
| authorships[0].institutions[0].display_name | Siemens (Germany) |
| authorships[0].institutions[1].id | https://openalex.org/I62916508 |
| authorships[0].institutions[1].ror | https://ror.org/02kkvpp62 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I62916508 |
| authorships[0].institutions[1].country_code | DE |
| authorships[0].institutions[1].display_name | Technical University of Munich |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yongjian Tang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Siemens AG, Munich, Germany, Technical University of Munich, Germany |
| authorships[1].author.id | https://openalex.org/A5023358460 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Rakebul Hasan |
| authorships[1].countries | DE |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I1325886976 |
| authorships[1].affiliations[0].raw_affiliation_string | Siemens AG, Munich, Germany |
| authorships[1].institutions[0].id | https://openalex.org/I1325886976 |
| authorships[1].institutions[0].ror | https://ror.org/059mq0909 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I1325886976 |
| authorships[1].institutions[0].country_code | DE |
| authorships[1].institutions[0].display_name | Siemens (Germany) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Rakebul Hasan |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Siemens AG, Munich, Germany |
| authorships[2].author.id | https://openalex.org/A5002518694 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5465-198X |
| authorships[2].author.display_name | Thomas A. Runkler |
| authorships[2].countries | DE |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I1325886976 |
| authorships[2].affiliations[0].raw_affiliation_string | Siemens AG, Munich, Germany |
| authorships[2].affiliations[1].institution_ids | https://openalex.org/I62916508 |
| authorships[2].affiliations[1].raw_affiliation_string | Technical University of Munich, Germany |
| authorships[2].institutions[0].id | https://openalex.org/I1325886976 |
| authorships[2].institutions[0].ror | https://ror.org/059mq0909 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I1325886976 |
| authorships[2].institutions[0].country_code | DE |
| authorships[2].institutions[0].display_name | Siemens (Germany) |
| authorships[2].institutions[1].id | https://openalex.org/I62916508 |
| authorships[2].institutions[1].ror | https://ror.org/02kkvpp62 |
| authorships[2].institutions[1].type | education |
| authorships[2].institutions[1].lineage | https://openalex.org/I62916508 |
| authorships[2].institutions[1].country_code | DE |
| authorships[2].institutions[1].display_name | Technical University of Munich |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Thomas Runkler |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Siemens AG, Munich, Germany, Technical University of Munich, Germany |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240936 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | FsPONER: Few-Shot Prompt Optimization for Named Entity Recognition in Domain-Specific Scenarios |
| has_fulltext | False |
| 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 | 0.9995999932289124 |
| 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/W3005759282, https://openalex.org/W3017222382, https://openalex.org/W3128216712, https://openalex.org/W3204019825, https://openalex.org/W3136915866, https://openalex.org/W4390279576, https://openalex.org/W2886890203, https://openalex.org/W2983934248, https://openalex.org/W4313535650, https://openalex.org/W1605730749 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 3 |
| locations_count | 1 |
| best_oa_location.id | doi:10.3233/faia240936 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210201731 |
| best_oa_location.source.issn | 0922-6389, 1879-8314 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 0922-6389 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Frontiers in artificial intelligence and applications |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | cc-by-nc |
| best_oa_location.pdf_url | https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240936 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | book-chapter |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Frontiers in Artificial Intelligence and Applications |
| best_oa_location.landing_page_url | https://doi.org/10.3233/faia240936 |
| primary_location.id | doi:10.3233/faia240936 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210201731 |
| primary_location.source.issn | 0922-6389, 1879-8314 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 0922-6389 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Frontiers in artificial intelligence and applications |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | cc-by-nc |
| primary_location.pdf_url | https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240936 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | book-chapter |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Frontiers in Artificial Intelligence and Applications |
| primary_location.landing_page_url | https://doi.org/10.3233/faia240936 |
| publication_date | 2024-10-16 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 6, 76, 92, 124, 133 |
| abstract_inverted_index.F1 | 174 |
| abstract_inverted_index.In | 156 |
| abstract_inverted_index.To | 69 |
| abstract_inverted_index.We | 128 |
| abstract_inverted_index.as | 137 |
| abstract_inverted_index.by | 170 |
| abstract_inverted_index.in | 66, 173 |
| abstract_inverted_index.of | 54, 62, 112, 126, 140 |
| abstract_inverted_index.on | 32, 48, 87, 94, 118 |
| abstract_inverted_index.to | 42 |
| abstract_inverted_index.we | 73 |
| abstract_inverted_index.10% | 172 |
| abstract_inverted_index.NER | 50, 89, 148 |
| abstract_inverted_index.and | 30, 83, 97, 108, 123, 144, 153 |
| abstract_inverted_index.for | 9, 24, 79 |
| abstract_inverted_index.has | 58 |
| abstract_inverted_index.its | 85 |
| abstract_inverted_index.new | 7 |
| abstract_inverted_index.the | 22, 55, 60, 138, 157 |
| abstract_inverted_index.– | 103 |
| abstract_inverted_index.BERT | 152 |
| abstract_inverted_index.LLMs | 102 |
| abstract_inverted_index.data | 162 |
| abstract_inverted_index.gap, | 72 |
| abstract_inverted_index.have | 4, 38 |
| abstract_inverted_index.need | 23 |
| abstract_inverted_index.none | 53 |
| abstract_inverted_index.rely | 31 |
| abstract_inverted_index.this | 71 |
| abstract_inverted_index.with | 16, 91, 132, 161, 165 |
| abstract_inverted_index.(NER) | 13 |
| abstract_inverted_index.LLaMA | 106, 154 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.Named | 10 |
| abstract_inverted_index.avoid | 21 |
| abstract_inverted_index.based | 117 |
| abstract_inverted_index.both. | 127 |
| abstract_inverted_index.data. | 35 |
| abstract_inverted_index.focus | 93 |
| abstract_inverted_index.fully | 43 |
| abstract_inverted_index.novel | 77 |
| abstract_inverted_index.their | 146 |
| abstract_inverted_index.these | 130 |
| abstract_inverted_index.three | 113 |
| abstract_inverted_index.using | 100 |
| abstract_inverted_index.while | 99 |
| abstract_inverted_index.(LLMs) | 3 |
| abstract_inverted_index.Entity | 11 |
| abstract_inverted_index.Models | 2 |
| abstract_inverted_index.TF-IDF | 121, 166 |
| abstract_inverted_index.method | 136 |
| abstract_inverted_index.models | 169 |
| abstract_inverted_index.number | 139 |
| abstract_inverted_index.random | 119 |
| abstract_inverted_index.score. | 175 |
| abstract_inverted_index.tasks. | 14 |
| abstract_inverted_index.2-chat, | 107 |
| abstract_inverted_index.2-chat. | 155 |
| abstract_inverted_index.FsPONER | 110, 164 |
| abstract_inverted_index.GPT-NER | 135 |
| abstract_inverted_index.Vicuna. | 109 |
| abstract_inverted_index.address | 70 |
| abstract_inverted_index.against | 150 |
| abstract_inverted_index.compare | 129 |
| abstract_inverted_index.general | 49 |
| abstract_inverted_index.methods | 20, 116, 131 |
| abstract_inverted_index.minimal | 33 |
| abstract_inverted_index.optimal | 147 |
| abstract_inverted_index.pathway | 8 |
| abstract_inverted_index.studies | 37 |
| abstract_inverted_index.Compared | 15 |
| abstract_inverted_index.FsPONER, | 75 |
| abstract_inverted_index.However, | 52 |
| abstract_inverted_index.Language | 1 |
| abstract_inverted_index.Previous | 36 |
| abstract_inverted_index.achieved | 39 |
| abstract_inverted_index.approach | 78 |
| abstract_inverted_index.conserve | 26 |
| abstract_inverted_index.consists | 111 |
| abstract_inverted_index.evaluate | 84, 145 |
| abstract_inverted_index.examples | 142 |
| abstract_inverted_index.few-shot | 64, 81, 114, 141 |
| abstract_inverted_index.learning | 65 |
| abstract_inverted_index.multiple | 101 |
| abstract_inverted_index.previous | 56 |
| abstract_inverted_index.prompts, | 82 |
| abstract_inverted_index.provided | 5 |
| abstract_inverted_index.vectors, | 122 |
| abstract_inverted_index.LLM-based | 63 |
| abstract_inverted_index.annotated | 34 |
| abstract_inverted_index.datasets, | 90 |
| abstract_inverted_index.increases | 143 |
| abstract_inverted_index.introduce | 74 |
| abstract_inverted_index.prompting | 19 |
| abstract_inverted_index.sampling, | 120 |
| abstract_inverted_index.scarcity, | 163 |
| abstract_inverted_index.scenarios | 160 |
| abstract_inverted_index.selection | 115 |
| abstract_inverted_index.surpasses | 167 |
| abstract_inverted_index.training, | 25 |
| abstract_inverted_index.BERT-based | 45 |
| abstract_inverted_index.GPT-4-32K, | 104 |
| abstract_inverted_index.approaches | 47, 57 |
| abstract_inverted_index.comparable | 40 |
| abstract_inverted_index.considered | 158 |
| abstract_inverted_index.efficiency | 61 |
| abstract_inverted_index.fine-tuned | 151, 168 |
| abstract_inverted_index.industrial | 95 |
| abstract_inverted_index.optimizing | 80 |
| abstract_inverted_index.real-world | 159 |
| abstract_inverted_index.resources, | 29 |
| abstract_inverted_index.scenarios. | 68 |
| abstract_inverted_index.supervised | 44 |
| abstract_inverted_index.LLM-powered | 18 |
| abstract_inverted_index.Recognition | 12 |
| abstract_inverted_index.benchmarks. | 51 |
| abstract_inverted_index.combination | 125 |
| abstract_inverted_index.fine-tuning | 46 |
| abstract_inverted_index.performance | 41, 86, 149 |
| abstract_inverted_index.substantial | 27 |
| abstract_inverted_index.fine-tuning, | 17 |
| abstract_inverted_index.investigated | 59 |
| abstract_inverted_index.maintenance, | 98 |
| abstract_inverted_index.approximately | 171 |
| abstract_inverted_index.computational | 28 |
| abstract_inverted_index.manufacturing | 96 |
| abstract_inverted_index.GPT-3.5-Turbo, | 105 |
| abstract_inverted_index.domain-specific | 67, 88 |
| abstract_inverted_index.general-purpose | 134 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 96 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/9 |
| sustainable_development_goals[0].score | 0.6100000143051147 |
| sustainable_development_goals[0].display_name | Industry, innovation and infrastructure |
| citation_normalized_percentile.value | 0.92160716 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |