Glenn Matlin
glennmatlin.bsky.social
Glenn Matlin
@glennmatlin.bsky.social
Ph.D. Computer Science, Georgia Institute of Technology — working on RAPID AI; Reasoning, Analysis, and Planning for Interactive Decision-making
Reposted by Glenn Matlin
#COLM2025 is starting. Find @glennmatlin.bsky.social to learn about why LLMs kinda, sorta, but don't really understand psychological suspense in stories.
Our work on Detecting Suspense in Stories will appear at COLM'25 arxiv.org/abs/2508.15794

Do LLMs know when stories are suspenseful?

We ran LLMs through a bunch of classical psychology suspense studies

The answer: kinda, sorta? Honestly, better than I expected. But the results are nuanced...

1/
October 6, 2025 at 3:07 PM
Reposted by Glenn Matlin
Hi all. I whipped up a blog post that give non-technical intuition behind how LLMs and chatbots work.

mark-riedl.medium.com/the-intuitio...

It's a variation on a talk I've given a few times to K-12 teachers and other non-technical LLM users.
The Intuition Behind How Large Language Models Work
Large Language Models (LLMs) are fancy artificial neural networks. But you don’t have time to learn the math or engineering. Unfortunately…
mark-riedl.medium.com
August 7, 2025 at 4:01 PM