Representation engineering: A top-down approach to ai transparency

A Zou, L Phan, S Chen, J Campbell, P Guo… - arXiv preprint arXiv …, 2023 - arxiv.org
In this paper, we identify and characterize the emerging area of representation engineering
(RepE), an approach to enhancing the transparency of AI systems that draws on insights …

Can generalist foundation models outcompete special-purpose tuning? case study in medicine

H Nori, YT Lee, S Zhang, D Carignan, R Edgar… - arXiv preprint arXiv …, 2023 - arxiv.org
Generalist foundation models such as GPT-4 have displayed surprising capabilities in a
wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot …

[HTML][HTML] Generative language models and open notes: exploring the promise and limitations

C Blease, J Torous, B McMillan, M Hägglund… - JMIR Medical …, 2024 - mededu.jmir.org
Patients' online record access (ORA) is growing worldwide. In some countries, including the
United States and Sweden, access is advanced with patients obtaining rapid access to their …

Development of a liver disease-Specific large language model chat Interface using retrieval augmented generation

J Ge, S Sun, J Owens, V Galvez, O Gologorskaya… - Hepatology, 2024 - journals.lww.com
Background: Large language models (LLMs) have significant capabilities in clinical
information processing tasks. Commercially available LLMs, however, are not optimized for …

Surveying Attitudinal Alignment Between Large Language Models Vs. Humans Towards 17 Sustainable Development Goals

Q Wu, Y Xu, T Xiao, Y Xiao, Y Li, T Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) have emerged as potent tools for advancing the United
Nations' Sustainable Development Goals (SDGs). However, the attitudinal disparities …

Large language models in medical and healthcare fields: applications, advances, and challenges

D Wang, S Zhang - Artificial Intelligence Review, 2024 - Springer
Large language models (LLMs) are increasingly recognized for their advanced language
capabilities, offering significant assistance in diverse areas like medical communication …

How susceptible are llms to logical fallacies?

A Payandeh, D Pluth, J Hosier, X Xiao… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper investigates the rational thinking capability of Large Language Models (LLMs) in
multi-round argumentative debates by exploring the impact of fallacious arguments on their …

Leveraging generative AI for clinical evidence synthesis needs to ensure trustworthiness

G Zhang, Q Jin, DJ McInerney, Y Chen, F Wang… - Journal of Biomedical …, 2024 - Elsevier
Evidence-based medicine promises to improve the quality of healthcare by empowering
medical decisions and practices with the best available evidence. The rapid growth of …

Mixed methods assessment of the influence of demographics on medical advice of ChatGPT

K Andreadis, DR Newman, C Twan… - Journal of the …, 2024 - academic.oup.com
Objectives To evaluate demographic biases in diagnostic accuracy and health advice
between generative artificial intelligence (AI)(ChatGPT GPT-4) and traditional symptom …

The LLM Will See You Now: Performance of ChatGPT on the Brazilian Radiology and Diagnostic Imaging and Mammography Board Examinations

H Trivedi, J Wawira Gichoya - Radiology: Artificial Intelligence, 2024 - pubs.rsna.org
Hari Trivedi, MD, is an assistant professor at Emory University in emergency radiology,
biomedical informatics, and emergency medicine. He co-directs the HITI (Healthcare AI …