Lucy Li

lucy3.bsky.social

14 October 2026 16:53

Models are sycophantic, and when they do challenge faulty or incorrect inputs, they're ambiguous and ineffective. In a new paper w/ a multilingual co-author team, we find that people may view LM responses that push back, yet still end up believing false content is true. arxiv.org/abs/2610.17703

Giovanni Luca Ciampaglia

glciampaglia.com

12 October 2026 22:11

Hi #CSCW2026! I'm excited to present today our new paper with @dowonkim.bsky.social & @cbuntain.bsky.social on understanding how young adults make sense of the news on their social media feeds. Here is a quick 🧵

Gavin Abercrombie

gavina.bsky.social

07 October 2026 16:59

Pleased to announce that NLPerspectives 6 will take place at EMNLP in autumn 2027 🌎

Angelina Wang

angelinawang.bsky.social

29 September 2026 20:28

Check out our new COLM oral paper led by Meera, where we use convergent and discriminant validity to show how benchmarks purporting to measure similar and dissimilar concepts correlate with each other in unexpected ways!

Hanna Wallach

hannawallach.bsky.social

29 September 2026 20:28

I'm super excited that this fun paper with @madesai.bsky.social, @angelinawang.bsky.social, and other fantastic collaborators will be presented as a spotlight oral at COLM next week!!! 🎉 Please come check it out if you'll be there!