Donya Rooein
@donyarn.bsky.social
Postdoc at MilaNLP, Bocconi University
Human-centered AI, NLP for Education
Human-centered AI, NLP for Education
Reposted by Donya Rooein
🎉 The @milanlp.bsky.social lab is excited to present 15 papers and 1 tutorial at #ACL2025 & workshops! Grateful to all our amazing collaborators, see everyone in Vienna! 🚀
July 16, 2025 at 12:11 PM
🎉 The @milanlp.bsky.social lab is excited to present 15 papers and 1 tutorial at #ACL2025 & workshops! Grateful to all our amazing collaborators, see everyone in Vienna! 🚀
Reposted by Donya Rooein
"Measuring Gender Bias in Language Models in Farsi" across tasks and models, showing how the linguistic and cultural context shapes bias
With Hamidreza Saffari, Mohammadamin Shafiei, @donyarn.bsky.social #GeBNLP2025
With Hamidreza Saffari, Mohammadamin Shafiei, @donyarn.bsky.social #GeBNLP2025
July 27, 2025 at 10:29 AM
"Measuring Gender Bias in Language Models in Farsi" across tasks and models, showing how the linguistic and cultural context shapes bias
With Hamidreza Saffari, Mohammadamin Shafiei, @donyarn.bsky.social #GeBNLP2025
With Hamidreza Saffari, Mohammadamin Shafiei, @donyarn.bsky.social #GeBNLP2025
Reposted by Donya Rooein
July 30, 2025 at 8:45 AM
Reposted by Donya Rooein
Today, we are releasing MSTS, a new Multimodal Safety Test Suite for vision-language models!
MSTS is exciting because it tests for safety risks *created by multimodality*. Each prompt consists of a text + image that *only in combination* reveal their full unsafe meaning.
🧵
MSTS is exciting because it tests for safety risks *created by multimodality*. Each prompt consists of a text + image that *only in combination* reveal their full unsafe meaning.
🧵
January 21, 2025 at 11:36 AM
Today, we are releasing MSTS, a new Multimodal Safety Test Suite for vision-language models!
MSTS is exciting because it tests for safety risks *created by multimodality*. Each prompt consists of a text + image that *only in combination* reveal their full unsafe meaning.
🧵
MSTS is exciting because it tests for safety risks *created by multimodality*. Each prompt consists of a text + image that *only in combination* reveal their full unsafe meaning.
🧵