Auditing LLMs and Twitter
Data Skeptic29 Tammi

Auditing LLMs and Twitter

Our guests, Erwan Le Merrer and Gilles Tredan, are long-time collaborators in graph theory and distributed systems. They share their expertise on applying graph-based approaches to understanding both large language model (LLM) hallucinations and shadow banning on social media platforms.

In this episode, listeners will learn how graph structures and metrics can reveal patterns in algorithmic behavior and platform moderation practices.

Key insights include the use of graph theory to evaluate LLM outputs, uncovering patterns in hallucinated graphs that might hint at the underlying structure and training data of the models, and applying epidemic models to analyze the uneven spread of shadow banning on Twitter.

-------------------------------

Want to listen ad-free? Try our Graphs Course? Join Data Skeptic+ for $5 / month of $50 / year

https://plus.dataskeptic.com

Jaksot(588)

Suosittua kategoriassa Tiede

rss-mita-tulisi-tietaa
tiedekulma-podcast
utelias-mieli
hippokrateen-vastaanotolla
docemilia
sotataidon-ytimessa
rss-poliisin-mieli
rss-lihavuudesta-podcast
radio-antro
rss-duodecim-lehti
rss-tiedetta-vai-tarinaa
filocast-filosofian-perusteet
menologeja-tutkimusmatka-vaihdevuosiin
rss-bios-podcast
rss-ammamafia
rss-laakaripodi
rss-ilmasto-kriisissa
rss-pandapodi
rss-ylistys-elaimille
rss-tervetta-skeptisyytta