Exploring the Boundaries of GPT-4 in Radiology Article Swipe
Qianchu Liu
,
Stephanie L. Hyland
,
Shruthi Bannur
,
Kenza Bouzid
,
Daniel C. Castro
,
Maria Teodora Wetscherek
,
Robert Tinn
,
Harshita Sharma
,
Fernando Pérez‐García
,
Anton Schwaighofer
,
Pranav Rajpurkar
,
Sameer Khanna
,
Hoifung Poon
,
Naoto Usuyama
,
Anja Thieme
,
Aditya V. Nori
,
Matthew P. Lungren
,
Ozan Oktay
,
Javier Alvarez-Valle
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.14573
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.14573
The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the text-based applications for radiology reports, comparing against state-of-the-art (SOTA) radiology-specific models. Exploring various prompting strategies, we evaluated GPT-4 on a diverse range of common radiology tasks and we found GPT-4 either outperforms or is on par with current SOTA radiology models. With zero-shot prompting, GPT-4 already obtains substantial gains ($\approx$ 10% absolute improvement) over radiology models in temporal sentence similarity classification (accuracy) and natural language inference ($F_1$). For tasks that require learning dataset-specific style or schema (e.g. findings summarisation), GPT-4 improves with example-based prompting and matches supervised SOTA. Our extensive error analysis with a board-certified radiologist shows GPT-4 has a sufficient level of radiology knowledge with only occasional errors in complex context that require nuanced domain knowledge. For findings summarisation, GPT-4 outputs are found to be overall comparable with existing manually-written impressions.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2310.14573
- https://arxiv.org/pdf/2310.14573
- OA Status
- green
- Cited By
- 2
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387929318
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387929318Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2310.14573Digital Object Identifier
- Title
-
Exploring the Boundaries of GPT-4 in RadiologyWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-23Full publication date if available
- Authors
-
Qianchu Liu, Stephanie L. Hyland, Shruthi Bannur, Kenza Bouzid, Daniel C. Castro, Maria Teodora Wetscherek, Robert Tinn, Harshita Sharma, Fernando Pérez‐García, Anton Schwaighofer, Pranav Rajpurkar, Sameer Khanna, Hoifung Poon, Naoto Usuyama, Anja Thieme, Aditya V. Nori, Matthew P. Lungren, Ozan Oktay, Javier Alvarez-ValleList of authors in order
- Landing page
-
https://arxiv.org/abs/2310.14573Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2310.14573Direct 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/2310.14573Direct OA link when available
- Concepts
-
Computer science, Schema (genetic algorithms), Inference, Artificial intelligence, Context (archaeology), Natural language processing, Domain (mathematical analysis), Machine learning, Radiology, Medicine, Biology, Mathematical analysis, Mathematics, PaleontologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4387929318 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2310.14573 |
| ids.doi | https://doi.org/10.48550/arxiv.2310.14573 |
| ids.openalex | https://openalex.org/W4387929318 |
| fwci | |
| type | preprint |
| title | Exploring the Boundaries of GPT-4 in Radiology |
| 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 | 0.9973999857902527 |
| 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 | 0.980400025844574 |
| 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/T11636 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.9787999987602234 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2718 |
| topics[2].subfield.display_name | Health Informatics |
| topics[2].display_name | Artificial Intelligence in Healthcare and Education |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.585139811038971 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C52146309 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5680363178253174 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7431116 |
| concepts[1].display_name | Schema (genetic algorithms) |
| concepts[2].id | https://openalex.org/C2776214188 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5672990083694458 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[2].display_name | Inference |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5408686995506287 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C2779343474 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4891543686389923 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[4].display_name | Context (archaeology) |
| concepts[5].id | https://openalex.org/C204321447 |
| concepts[5].level | 1 |
| concepts[5].score | 0.44668540358543396 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[5].display_name | Natural language processing |
| concepts[6].id | https://openalex.org/C36503486 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4277758002281189 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11235244 |
| concepts[6].display_name | Domain (mathematical analysis) |
| concepts[7].id | https://openalex.org/C119857082 |
| concepts[7].level | 1 |
| concepts[7].score | 0.368158757686615 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[7].display_name | Machine learning |
| concepts[8].id | https://openalex.org/C126838900 |
| concepts[8].level | 1 |
| concepts[8].score | 0.34110331535339355 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q77604 |
| concepts[8].display_name | Radiology |
| concepts[9].id | https://openalex.org/C71924100 |
| concepts[9].level | 0 |
| concepts[9].score | 0.18032774329185486 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[9].display_name | Medicine |
| concepts[10].id | https://openalex.org/C86803240 |
| concepts[10].level | 0 |
| concepts[10].score | 0.1237821877002716 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[10].display_name | Biology |
| concepts[11].id | https://openalex.org/C134306372 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[11].display_name | Mathematical analysis |
| concepts[12].id | https://openalex.org/C33923547 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[12].display_name | Mathematics |
| 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 |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.585139811038971 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/schema |
| keywords[1].score | 0.5680363178253174 |
| keywords[1].display_name | Schema (genetic algorithms) |
| keywords[2].id | https://openalex.org/keywords/inference |
| keywords[2].score | 0.5672990083694458 |
| keywords[2].display_name | Inference |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5408686995506287 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/context |
| keywords[4].score | 0.4891543686389923 |
| keywords[4].display_name | Context (archaeology) |
| keywords[5].id | https://openalex.org/keywords/natural-language-processing |
| keywords[5].score | 0.44668540358543396 |
| keywords[5].display_name | Natural language processing |
| keywords[6].id | https://openalex.org/keywords/domain |
| keywords[6].score | 0.4277758002281189 |
| keywords[6].display_name | Domain (mathematical analysis) |
| keywords[7].id | https://openalex.org/keywords/machine-learning |
| keywords[7].score | 0.368158757686615 |
| keywords[7].display_name | Machine learning |
| keywords[8].id | https://openalex.org/keywords/radiology |
| keywords[8].score | 0.34110331535339355 |
| keywords[8].display_name | Radiology |
| keywords[9].id | https://openalex.org/keywords/medicine |
| keywords[9].score | 0.18032774329185486 |
| keywords[9].display_name | Medicine |
| keywords[10].id | https://openalex.org/keywords/biology |
| keywords[10].score | 0.1237821877002716 |
| keywords[10].display_name | Biology |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2310.14573 |
| 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/2310.14573 |
| 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/2310.14573 |
| locations[1].id | doi:10.48550/arxiv.2310.14573 |
| 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 | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2310.14573 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5110005418 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Qianchu Liu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Liu, Qianchu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5020430024 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4812-792X |
| authorships[1].author.display_name | Stephanie L. Hyland |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Hyland, Stephanie |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5081683131 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5750-7628 |
| authorships[2].author.display_name | Shruthi Bannur |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Bannur, Shruthi |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5080583641 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5864-2792 |
| authorships[3].author.display_name | Kenza Bouzid |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Bouzid, Kenza |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5037843387 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-6829-7045 |
| authorships[4].author.display_name | Daniel C. Castro |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Castro, Daniel C. |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5008697579 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-2924-7587 |
| authorships[5].author.display_name | Maria Teodora Wetscherek |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Wetscherek, Maria Teodora |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5073496354 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-0182-7280 |
| authorships[6].author.display_name | Robert Tinn |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Tinn, Robert |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5056301773 |
| authorships[7].author.orcid | https://orcid.org/0000-0003-4683-2606 |
| authorships[7].author.display_name | Harshita Sharma |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Sharma, Harshita |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5054482170 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-9090-3024 |
| authorships[8].author.display_name | Fernando Pérez‐García |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Pérez-García, Fernando |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5010707054 |
| authorships[9].author.orcid | https://orcid.org/0000-0003-1557-0527 |
| authorships[9].author.display_name | Anton Schwaighofer |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Schwaighofer, Anton |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5001094226 |
| authorships[10].author.orcid | https://orcid.org/0000-0002-8030-3727 |
| authorships[10].author.display_name | Pranav Rajpurkar |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Rajpurkar, Pranav |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5081388398 |
| authorships[11].author.orcid | |
| authorships[11].author.display_name | Sameer Khanna |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Khanna, Sameer Tajdin |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5019494985 |
| authorships[12].author.orcid | https://orcid.org/0000-0002-9067-0918 |
| authorships[12].author.display_name | Hoifung Poon |
| authorships[12].author_position | middle |
| authorships[12].raw_author_name | Poon, Hoifung |
| authorships[12].is_corresponding | False |
| authorships[13].author.id | https://openalex.org/A5010756260 |
| authorships[13].author.orcid | https://orcid.org/0000-0003-0888-929X |
| authorships[13].author.display_name | Naoto Usuyama |
| authorships[13].author_position | middle |
| authorships[13].raw_author_name | Usuyama, Naoto |
| authorships[13].is_corresponding | False |
| authorships[14].author.id | https://openalex.org/A5015598933 |
| authorships[14].author.orcid | https://orcid.org/0000-0002-9639-5531 |
| authorships[14].author.display_name | Anja Thieme |
| authorships[14].author_position | middle |
| authorships[14].raw_author_name | Thieme, Anja |
| authorships[14].is_corresponding | False |
| authorships[15].author.id | https://openalex.org/A5111937381 |
| authorships[15].author.orcid | |
| authorships[15].author.display_name | Aditya V. Nori |
| authorships[15].author_position | middle |
| authorships[15].raw_author_name | Nori, Aditya V. |
| authorships[15].is_corresponding | False |
| authorships[16].author.id | https://openalex.org/A5038969629 |
| authorships[16].author.orcid | https://orcid.org/0000-0002-8591-5861 |
| authorships[16].author.display_name | Matthew P. Lungren |
| authorships[16].author_position | middle |
| authorships[16].raw_author_name | Lungren, Matthew P. |
| authorships[16].is_corresponding | False |
| authorships[17].author.id | https://openalex.org/A5038400548 |
| authorships[17].author.orcid | https://orcid.org/0000-0003-2976-0874 |
| authorships[17].author.display_name | Ozan Oktay |
| authorships[17].author_position | middle |
| authorships[17].raw_author_name | Oktay, Ozan |
| authorships[17].is_corresponding | False |
| authorships[18].author.id | https://openalex.org/A5050558499 |
| authorships[18].author.orcid | https://orcid.org/0000-0003-0906-4177 |
| authorships[18].author.display_name | Javier Alvarez-Valle |
| authorships[18].author_position | last |
| authorships[18].raw_author_name | Alvarez-Valle, Javier |
| authorships[18].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/2310.14573 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Exploring the Boundaries of GPT-4 in Radiology |
| 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 | 0.9973999857902527 |
| 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/W2055243143, https://openalex.org/W4321636575, https://openalex.org/W1986418932, https://openalex.org/W2357796999, https://openalex.org/W2045526782, https://openalex.org/W2741131631, https://openalex.org/W2156919374, https://openalex.org/W2033101018, https://openalex.org/W1984019423, https://openalex.org/W2961085424 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2310.14573 |
| 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/2310.14573 |
| 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/2310.14573 |
| primary_location.id | pmh:oai:arXiv.org:2310.14573 |
| 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/2310.14573 |
| 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/2310.14573 |
| publication_date | 2023-10-23 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 18, 64, 138, 144 |
| abstract_inverted_index.In | 26 |
| abstract_inverted_index.be | 170 |
| abstract_inverted_index.in | 101, 154 |
| abstract_inverted_index.is | 78 |
| abstract_inverted_index.of | 3, 35, 67, 147 |
| abstract_inverted_index.on | 31, 43, 63, 79 |
| abstract_inverted_index.or | 77, 119 |
| abstract_inverted_index.so | 41 |
| abstract_inverted_index.to | 169 |
| abstract_inverted_index.we | 29, 60, 72 |
| abstract_inverted_index.10% | 95 |
| abstract_inverted_index.For | 112, 162 |
| abstract_inverted_index.LLM | 40 |
| abstract_inverted_index.Our | 133 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 24, 71, 107, 129 |
| abstract_inverted_index.are | 167 |
| abstract_inverted_index.for | 47 |
| abstract_inverted_index.has | 9, 143 |
| abstract_inverted_index.par | 80 |
| abstract_inverted_index.the | 12, 33, 37, 44 |
| abstract_inverted_index.SOTA | 83 |
| abstract_inverted_index.With | 86 |
| abstract_inverted_index.far, | 42 |
| abstract_inverted_index.most | 38 |
| abstract_inverted_index.only | 151 |
| abstract_inverted_index.over | 98 |
| abstract_inverted_index.that | 114, 157 |
| abstract_inverted_index.this | 27 |
| abstract_inverted_index.with | 81, 126, 137, 150, 173 |
| abstract_inverted_index.(e.g. | 121 |
| abstract_inverted_index.GPT-4 | 62, 74, 89, 124, 142, 165 |
| abstract_inverted_index.SOTA. | 132 |
| abstract_inverted_index.error | 135 |
| abstract_inverted_index.focus | 30 |
| abstract_inverted_index.found | 73, 168 |
| abstract_inverted_index.gains | 93 |
| abstract_inverted_index.large | 5 |
| abstract_inverted_index.level | 146 |
| abstract_inverted_index.model | 21 |
| abstract_inverted_index.range | 66 |
| abstract_inverted_index.shows | 141 |
| abstract_inverted_index.style | 118 |
| abstract_inverted_index.tasks | 70, 113 |
| abstract_inverted_index.(LLMs) | 8 |
| abstract_inverted_index.(SOTA) | 53 |
| abstract_inverted_index.GPT-4, | 36 |
| abstract_inverted_index.across | 22 |
| abstract_inverted_index.common | 68 |
| abstract_inverted_index.domain | 160 |
| abstract_inverted_index.either | 75 |
| abstract_inverted_index.errors | 153 |
| abstract_inverted_index.models | 7, 100 |
| abstract_inverted_index.paper, | 28 |
| abstract_inverted_index.recent | 1 |
| abstract_inverted_index.schema | 120 |
| abstract_inverted_index.against | 51 |
| abstract_inverted_index.already | 90 |
| abstract_inverted_index.capable | 39 |
| abstract_inverted_index.changed | 11 |
| abstract_inverted_index.complex | 155 |
| abstract_inverted_index.context | 156 |
| abstract_inverted_index.current | 82 |
| abstract_inverted_index.diverse | 65 |
| abstract_inverted_index.domains | 23 |
| abstract_inverted_index.matches | 130 |
| abstract_inverted_index.models. | 55, 85 |
| abstract_inverted_index.natural | 13, 108 |
| abstract_inverted_index.nuanced | 159 |
| abstract_inverted_index.obtains | 91 |
| abstract_inverted_index.outputs | 166 |
| abstract_inverted_index.overall | 171 |
| abstract_inverted_index.require | 115, 158 |
| abstract_inverted_index.success | 2 |
| abstract_inverted_index.towards | 17 |
| abstract_inverted_index.unified | 19 |
| abstract_inverted_index.various | 57 |
| abstract_inverted_index.($F_1$). | 111 |
| abstract_inverted_index.absolute | 96 |
| abstract_inverted_index.analysis | 136 |
| abstract_inverted_index.existing | 174 |
| abstract_inverted_index.findings | 122, 163 |
| abstract_inverted_index.improves | 125 |
| abstract_inverted_index.language | 6, 14, 109 |
| abstract_inverted_index.learning | 116 |
| abstract_inverted_index.paradigm | 16 |
| abstract_inverted_index.reports, | 49 |
| abstract_inverted_index.sentence | 103 |
| abstract_inverted_index.temporal | 102 |
| abstract_inverted_index.Exploring | 56 |
| abstract_inverted_index.assessing | 32 |
| abstract_inverted_index.comparing | 50 |
| abstract_inverted_index.evaluated | 61 |
| abstract_inverted_index.extensive | 134 |
| abstract_inverted_index.inference | 110 |
| abstract_inverted_index.knowledge | 149 |
| abstract_inverted_index.prompting | 58, 128 |
| abstract_inverted_index.radiology | 48, 69, 84, 99, 148 |
| abstract_inverted_index.zero-shot | 87 |
| abstract_inverted_index.($\approx$ | 94 |
| abstract_inverted_index.(accuracy) | 106 |
| abstract_inverted_index.comparable | 172 |
| abstract_inverted_index.foundation | 20 |
| abstract_inverted_index.knowledge. | 161 |
| abstract_inverted_index.occasional | 152 |
| abstract_inverted_index.processing | 15 |
| abstract_inverted_index.prompting, | 88 |
| abstract_inverted_index.similarity | 104 |
| abstract_inverted_index.sufficient | 145 |
| abstract_inverted_index.supervised | 131 |
| abstract_inverted_index.text-based | 45 |
| abstract_inverted_index.outperforms | 76 |
| abstract_inverted_index.performance | 34 |
| abstract_inverted_index.radiologist | 140 |
| abstract_inverted_index.strategies, | 59 |
| abstract_inverted_index.substantial | 92 |
| abstract_inverted_index.applications | 46 |
| abstract_inverted_index.impressions. | 176 |
| abstract_inverted_index.improvement) | 97 |
| abstract_inverted_index.applications. | 25 |
| abstract_inverted_index.example-based | 127 |
| abstract_inverted_index.significantly | 10 |
| abstract_inverted_index.classification | 105 |
| abstract_inverted_index.general-domain | 4 |
| abstract_inverted_index.summarisation, | 164 |
| abstract_inverted_index.board-certified | 139 |
| abstract_inverted_index.summarisation), | 123 |
| abstract_inverted_index.dataset-specific | 117 |
| abstract_inverted_index.manually-written | 175 |
| abstract_inverted_index.state-of-the-art | 52 |
| abstract_inverted_index.radiology-specific | 54 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 19 |
| 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 |