Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Transgenic Plants02:50

Transgenic Plants

7.3K
Recombinant DNA technology called transgenesis is often used to add a foreign gene or remove a detrimental gene from an organism. Such genetically modified organisms are called transgenic organisms.
The first-ever transgenic plant was a tobacco plant developed in 1983 that showed resistance against the tobacco mosaic virus. Since then, many transgenic plants have been developed and commercialized for improving the agricultural, ornamental, and horticultural value of a crop plant. Transgenic...
7.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Tightly coupled equivariant flow matching for molecular docking with multimodal physical constraints.

Molecular diversity·2026
Same author

KLaR: fusing knowledge graphs and language models for biomedical target discovery.

Bioinformatics (Oxford, England)·2026
Same author

Chain-Mobility-Enabled 1D Lanthanide Coordination Polymer Glassy Scintillators for Underwater X-Ray Videography.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

PAIRMAP: A Unified Geometry-Aware Pairwise-Map Framework for Molecular Representation Learning.

Journal of chemical information and modeling·2026
Same author

Machine learning in the diagnosis of Hirschsprung disease: a systematic review and meta-analysis.

Pediatric surgery international·2026
Same author

EC-Dock: A Fast Equivariant Consistency Model for Molecular Docking and Virtual Screening.

Journal of chemical information and modeling·2026

Related Experiment Video

Updated: Jul 17, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

617

An extensive benchmark study on biomedical text generation and mining with ChatGPT.

Qijie Chen1, Haotong Sun1, Haoyang Liu2,3

  • 1AIDD, Mindrank AI Ltd, Zhejiang 310000, China.

Bioinformatics (Oxford, England)
|September 8, 2023
PubMed
Summary

Large language models like ChatGPT show promise in biomedical text analysis but do not yet match state-of-the-art performance. Further research is needed to improve their capabilities in specialized domains.

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

267
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

798

Related Experiment Videos

Last Updated: Jul 17, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

617
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

267
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

798

Area of Science:

  • Biomedical Natural Language Processing
  • Artificial Intelligence in Medicine

Background:

  • Recent advancements in natural language processing (NLP) and deep learning have significantly improved large language models (LLMs).
  • ChatGPT, built on GPT-3.5 and GPT-4, demonstrates strong general language understanding and reasoning abilities.
  • Exploration into ChatGPT's capacity for specialized domains, particularly the biomedical field, is a growing area of interest.

Purpose of the Study:

  • To comprehensively benchmark ChatGPT's performance on various biomedical text-related tasks.
  • To evaluate its effectiveness in understanding, reasoning, and generating biomedical text.
  • To identify the limitations of ChatGPT, specifically versions based on GPT-3.5, in this domain.

Main Methods:

  • Utilized datasets from the BLURB benchmark, including biomedical abstracts and clinical trial descriptions.
  • Evaluated ChatGPT on standard NLP tasks such as named entity recognition, relation extraction, sentence similarity, question answering, and document classification.
  • Prompts used in the experiments are detailed within the article.

Main Results:

  • ChatGPT achieved a BLURB score of 58.50, while the state-of-the-art model scored 84.30.
  • Demonstrated ChatGPT's versatility across multiple biomedical NLP tasks.
  • Highlighted specific limitations of ChatGPT (GPT-3.5) in complex biomedical text processing.

Conclusions:

  • ChatGPT exhibits notable effectiveness and versatility in biomedical text understanding, reasoning, and generation.
  • Current performance indicates that ChatGPT, particularly GPT-3.5, has limitations in specialized biomedical applications compared to state-of-the-art models.
  • Further development is required to enhance LLM capabilities for advanced biomedical NLP tasks.