Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366460253> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4366460253 abstract "Recently, ChatGPT and GPT-4 have emerged and gained immense global attention due to their unparalleled performance in language processing. Despite demonstrating impressive capability in various open-domain tasks, their adequacy in highly specific fields like radiology remains untested. Radiology presents unique linguistic phenomena distinct from open-domain data due to its specificity and complexity. Assessing the performance of large language models (LLMs) in such specific domains is crucial not only for a thorough evaluation of their overall performance but also for providing valuable insights into future model design directions: whether model design should be generic or domain-specific. To this end, in this study, we evaluate the performance of ChatGPT/GPT-4 on a radiology NLI task and compare it to other models fine-tuned specifically on task-related data samples. We also conduct a comprehensive investigation on ChatGPT/GPT-4's reasoning ability by introducing varying levels of inference difficulty. Our results show that 1) GPT-4 outperforms ChatGPT in the radiology NLI task; 2) other specifically fine-tuned models require significant amounts of data samples to achieve comparable performance to ChatGPT/GPT-4. These findings demonstrate that constructing a generic model that is capable of solving various tasks across different domains is feasible." @default.
- W4366460253 created "2023-04-22" @default.
- W4366460253 creator A5000937401 @default.
- W4366460253 creator A5009232538 @default.
- W4366460253 creator A5010632162 @default.
- W4366460253 creator A5015845559 @default.
- W4366460253 creator A5021541475 @default.
- W4366460253 creator A5023538893 @default.
- W4366460253 creator A5038582366 @default.
- W4366460253 creator A5041058074 @default.
- W4366460253 creator A5044757881 @default.
- W4366460253 creator A5057640513 @default.
- W4366460253 creator A5058429770 @default.
- W4366460253 creator A5068129399 @default.
- W4366460253 creator A5071037763 @default.
- W4366460253 creator A5074942308 @default.
- W4366460253 creator A5075390210 @default.
- W4366460253 date "2023-04-18" @default.
- W4366460253 modified "2023-09-27" @default.
- W4366460253 title "Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task" @default.
- W4366460253 doi "https://doi.org/10.48550/arxiv.2304.09138" @default.
- W4366460253 hasPublicationYear "2023" @default.
- W4366460253 type Work @default.
- W4366460253 citedByCount "0" @default.
- W4366460253 crossrefType "posted-content" @default.
- W4366460253 hasAuthorship W4366460253A5000937401 @default.
- W4366460253 hasAuthorship W4366460253A5009232538 @default.
- W4366460253 hasAuthorship W4366460253A5010632162 @default.
- W4366460253 hasAuthorship W4366460253A5015845559 @default.
- W4366460253 hasAuthorship W4366460253A5021541475 @default.
- W4366460253 hasAuthorship W4366460253A5023538893 @default.
- W4366460253 hasAuthorship W4366460253A5038582366 @default.
- W4366460253 hasAuthorship W4366460253A5041058074 @default.
- W4366460253 hasAuthorship W4366460253A5044757881 @default.
- W4366460253 hasAuthorship W4366460253A5057640513 @default.
- W4366460253 hasAuthorship W4366460253A5058429770 @default.
- W4366460253 hasAuthorship W4366460253A5068129399 @default.
- W4366460253 hasAuthorship W4366460253A5071037763 @default.
- W4366460253 hasAuthorship W4366460253A5074942308 @default.
- W4366460253 hasAuthorship W4366460253A5075390210 @default.
- W4366460253 hasBestOaLocation W43664602531 @default.
- W4366460253 hasConcept C115903868 @default.
- W4366460253 hasConcept C119857082 @default.
- W4366460253 hasConcept C127413603 @default.
- W4366460253 hasConcept C134306372 @default.
- W4366460253 hasConcept C135257023 @default.
- W4366460253 hasConcept C154945302 @default.
- W4366460253 hasConcept C201995342 @default.
- W4366460253 hasConcept C204321447 @default.
- W4366460253 hasConcept C2776214188 @default.
- W4366460253 hasConcept C2780451532 @default.
- W4366460253 hasConcept C33923547 @default.
- W4366460253 hasConcept C36503486 @default.
- W4366460253 hasConcept C41008148 @default.
- W4366460253 hasConceptScore W4366460253C115903868 @default.
- W4366460253 hasConceptScore W4366460253C119857082 @default.
- W4366460253 hasConceptScore W4366460253C127413603 @default.
- W4366460253 hasConceptScore W4366460253C134306372 @default.
- W4366460253 hasConceptScore W4366460253C135257023 @default.
- W4366460253 hasConceptScore W4366460253C154945302 @default.
- W4366460253 hasConceptScore W4366460253C201995342 @default.
- W4366460253 hasConceptScore W4366460253C204321447 @default.
- W4366460253 hasConceptScore W4366460253C2776214188 @default.
- W4366460253 hasConceptScore W4366460253C2780451532 @default.
- W4366460253 hasConceptScore W4366460253C33923547 @default.
- W4366460253 hasConceptScore W4366460253C36503486 @default.
- W4366460253 hasConceptScore W4366460253C41008148 @default.
- W4366460253 hasLocation W43664602531 @default.
- W4366460253 hasOpenAccess W4366460253 @default.
- W4366460253 hasPrimaryLocation W43664602531 @default.
- W4366460253 hasRelatedWork W1716025118 @default.
- W4366460253 hasRelatedWork W2081647779 @default.
- W4366460253 hasRelatedWork W2511279186 @default.
- W4366460253 hasRelatedWork W2949992439 @default.
- W4366460253 hasRelatedWork W2963058055 @default.
- W4366460253 hasRelatedWork W2963351832 @default.
- W4366460253 hasRelatedWork W2990109640 @default.
- W4366460253 hasRelatedWork W3107474891 @default.
- W4366460253 hasRelatedWork W3172706523 @default.
- W4366460253 hasRelatedWork W3185852197 @default.
- W4366460253 isParatext "false" @default.
- W4366460253 isRetracted "false" @default.
- W4366460253 workType "article" @default.