Our paper is out! 🎉
As part of my research at @oii.ox.ac.uk under the supervision of @rocher.lc and @computermacgyver.bsky.social, I built a language model to help human rights analysts crowdsource reports of gun violence.
The paper was recently published at ACM CSCW 👇
dl.acm.org/doi/10.1145/...
I'm humbled to have been selected as the next director of @oii.ox.ac.uk . I look forward to working with colleagues and friends to shape the next saga in our department's story
Social media platforms operate globally, but do they allocate human moderation equitably across languages?
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
Congratulations, @manueltonneau.bsky.social
🏆 Thrilled to share that our HateDay paper has received an Outstanding Paper Award at #ACL2025
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...
Using #LLMs to improve claim matching and #misinformation response. Come see our poster at #ACL2025NLP now (#430) or read the paper.
aclanthology.org/2025.finding...
If you missed this presentation, check out the paper here:
aclanthology.org/2025.acl-lon...
Overview of OII #ACL2025 presentations at the link below. Please say hi if you're here
www.oii.ox.ac.uk/news-events/...
The worst happened. We were DOGE’d. Our NSF funding is gone.
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
📈Out today in @PNASNews!📈
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.
🧵:
Can we detect #hatespeech at scale on social media?
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
🧵