Reposted by: Scott A. Hale, Aleksandra Urman
Our new WP shows the answer is no:
-Millions of users post in languages with zero moderators
-Where mods exist, mod count relative to content volume varies widely across langs
osf.io/amfws
Reposted by: Scott A. Hale
Big thanks to my wonderful co-authors: @deeliu97.bsky.social, Niyati, @computermacgyver.bsky.social, Sam, Victor, and @paul-rottger.bsky.social!
Thread 👇and data avail at huggingface.co/datasets/man...
aclanthology.org/2025.finding...
aclanthology.org/2025.acl-lon...
www.oii.ox.ac.uk/news-events/...
Reposted by: Scott A. Hale, Joanna Bryson, Helen Margetts , and 1 more Scott A. Hale, Joanna Bryson, Helen Margetts, Mohsen Mosleh
In a large pre-registered experiment (n=25,982), we find evidence that scaling the size of LLMs yields sharply diminishing persuasive returns for static political messages.
🧵:
So now there’s nothing stopping me from sharing Expert Voices Together, a crisis response system for US-based researchers and journalists facing harassment.
It's a true passion project. 🧵 1/
expertvoicestogether.org
Reposted by: Scott A. Hale
To answer this, we introduce 🤬HateDay🗓️, a global hate speech dataset representative of a day on Twitter.
The answer: not really! Detection perf is low and overestimated by traditional eval methods
arxiv.org/abs/2411.15462
🧵
