Lesley Blum

ORCID: 0009-0006-4145-094X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Artificial Intelligence in Healthcare and Education
  • Machine Learning in Healthcare
  • Natural Language Processing Techniques
  • Multimodal Machine Learning Applications
  • Workplace Violence and Bullying

University of California, Los Angeles
2024

BackgroundIn recent years, significant breakthroughs have been made in the field of natural language processing, particularly with development large models (LLMs). LLMs demonstrated remarkable capabilities on benchmarks related to general medical question answering, but there are fewer data about their performance subspecialty fields and studies still comparing many available LLMs. These potential be used as a part adaptive physician training, copilot applications, digital patient...

10.1056/aidbp2300092 article EN public-domain NEJM AI 2024-01-17

In recent years, there have been significant breakthroughs in the field of natural language processing, particularly with development large models (LLMs). These LLMs showcased remarkable capabilities on various benchmarks. healthcare field, exact role and other future AI will play remains unclear. There is a potential for these to be used as part adaptive physician training, medical co-pilot applications, digital patient interaction scenarios. The ability participate training care depend...

10.48550/arxiv.2308.04709 preprint EN other-oa arXiv (Cornell University) 2023-01-01

Open-source LLMs have shown great potential as fine-tuned chatbots, and demonstrate robust abilities in reasoning surpass many existing benchmarks. Retrieval-Augmented Generation (RAG) is a technique for improving the performance of on tasks that models weren't explicitly trained on, by leveraging external knowledge databases. Numerous studies demonstrated effectiveness RAG to more successfully accomplish downstream when using vector datasets consist relevant background information. It has...

10.48550/arxiv.2407.14609 preprint EN arXiv (Cornell University) 2024-07-19
Coming Soon ...