Prudent Promotion, Steady Development: Capability and Safety Considerations for Applying Large Language Models in Medicine
Communications in Computer and Information Science, ISSN: 1865-0937, Vol: 2059 CCIS, Page: 110-123
2024
- 2Captures
Metric Options: CountsSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Metrics Details
- Captures2
- Readers2
Conference Paper Description
The powerful capabilities of large language models (LLMs) in the medical field have been affirmed by various benchmark tests. However, safety assessments are indispensable for high-risk medical applications. We systematically analyzed LLMs, including their technical principles, applicability in healthcare, medical capability assessment, potential security risks, and countermeasures. The study found that LLMs demonstrate strong capabilities in medical text processing, decision support, and text generation, but also have risks like “hallucination”. To ensure safe and effective applications of LLMs, we analyzed the causes of hallucination and proposed using output detection and prompting techniques to mitigate hallucinations generated by LLMs. The results affirm that LLMs can advance AI innovation in healthcare, but need to be introduced prudently without comprehensive safety assessments.
Bibliographic Details
http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85190676929&origin=inward; http://dx.doi.org/10.1007/978-981-97-1280-9_9; https://link.springer.com/10.1007/978-981-97-1280-9_9; https://dx.doi.org/10.1007/978-981-97-1280-9_9; https://link.springer.com/chapter/10.1007/978-981-97-1280-9_9
Springer Science and Business Media LLC
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know