Explainable Explainability for Clinical LLMs

Mon, 15 Jul 2024 00:00:00 +0000

Discussions of explainability for large language models (LLMs) tend to focus on methods that identify what parts of a neural network encode certain concepts or words, with the hope that by illuminating the meaning of parts of the LLM “black box” we can be certain of how it is making a decision. These methods resemble those used in convolutional neural network architectures processing imaging data from, say, a CT scan, where parts of the source image important to the label are highlighted to help humans understand how the categorization was performed.

Semantic Entropy to Detect Confabulation in Large Language Models (Farquhar et al.)

Tue, 25 Jun 2024 00:00:00 +0000

LLMs Can Make Stuff Up
#

Most people who play around with ChatGPT or another LLM (and are not famous) have had the experience of asking about themselves and receiving convincing but wrong BS. Here’s what happens when I ask Llama 3 about myself:

>>> Tell me about Scott Gilmore, M.D. who trained at Christiana.

Scott Gilmore, MD, is an American orthopedic surgeon and researcher. He received his medical degree from Jefferson Medical College and completed his residency in orthopedic surgery at ChristianaCare Health System (then known as Christiana Healthcare System) in Wilmington, Delaware.

I’m not an orthopedic surgeon (I trained in EM), and I didn’t go to Jefferson (Wake Forest), etc. etc. …

AI Safety on Scott Gilmore, MD

Explainable Explainability for Clinical LLMs

Semantic Entropy to Detect Confabulation in Large Language Models (Farquhar et al.)

LLMs Can Make Stuff Up #

LLMs Can Make Stuff Up
#