π¨New Paper!π¨ How do reasoning LLMs handle inferences that have no deterministic answer? We find that they diverge from humans in some significant ways, and fail to reflect human uncertaintyβ¦ π§΅(1/10)
Our new paper in #PNAS (bit.ly/4fcWfma) presents a surprising findingβwhen words change meaning, older speakers rapidly adopt the new usage; inter-generational differences are often minor.
w/ Michelle Yang, βͺ@sivareddyg.bsky.socialβ¬ , @msonderegger.bsky.socialβ¬ and @dallascard.bsky.socialβ¬π(1/12)
Huge congratulations to Dr. @vernadankers.bsky.social for passing her viva today! π₯³π
It's truly been an honour sharing the PhD journey with you. I wasnβt ready for the void your sudden departure left (in the office and in my life!).
Your new colleagues are lucky to have you! π₯Ίπ₯°
A blizzard is raging through Montreal when your friend says βLooks like Florida out there!β Humans easily interpret irony, while LLMs struggle with it. We propose a π³π©π¦π΅π°π³πͺπ€π’π-π΄π΅π³π’π΅π¦π¨πΊ-π’πΈπ’π³π¦ probabilistic framework as a solution.
Paper: arxiv.org/abs/2506.09301 to appear @ #ACL2025 (Main)
Book cover - Lost in Automatic Translation: Navigating Life in English in the Age of Language Technologies. By Vered Shwartz. Publisher: Cambridge University Press.
I guess that now that I have 1% of my Twitter followers follow me here π , I should announce it here too for those of you no longer checking Twitter: my nonfiction book, "Lost in Automatic Translation" is coming out this July: lostinautomatictranslation.com. I'm very excited to share it with you!
Congratulations to Mila members @adadtur.bsky.social , Gaurav Kamath and @sivareddyg.bsky.social for their SAC award at NAACL! Check out Ada's talk in Session I: Oral/Poster 6. Paper: arxiv.org/abs/2502.05670
π Reminder & Call for #VLMs4All @ #CVPR2025!
Help shape the future of culturally aware & geo-diverse VLMs:
βοΈ Challenges: Deadline: Apr 15 πhttps://sites.google.com/view/vlms4all/challenges
π Papers (4pg): Deadline: Apr 22 πhttps://sites.google.com/view/vlms4all/call-for-papers
Join us!
Our DeepSeek-R1 'Thoughtology' paper π§ π‘brings a wealth of interesting insights into analyzing reasoning chains and across a variety of tasks.
Check it out!
mcgill-nlp.github.io/thoughtology/
π Diversity in AI matters! Excited to be part of the VLMs-4-All @CVPR 2025 Workshop, where we push for geo-diverse & culturally aware Vision-Language Models! Submit your papers now, join the challenges & engage in vital discussions. ππ₯ #CVPR2025 #VLMs4All2025
Instruction-following retrievers can efficiently and accurately search for harmful and sensitive information on the internet! ππ£
Retrievers need to be aligned too! π¨π¨π¨
Work done with the wonderful Nick and @sivareddyg.bsky.social
π mcgill-nlp.github.io/malicious-ir/
Thread: π§΅π
π¨π¨π¨ Checkout our new position paper on rethinking LLM alignment through social, economic, and contractual frameworks! ππΌβοΈ
Full paper: arxiv.org/abs/2503.00069
How should AI align with society? Letβs discuss!π
Presented the AURORA paper together with some of the awesome co-authors Chris Pal @sivareddyg.bsky.social and @ludolara.bsky.social from @Mila_Quebec
Tons of fun, 3h of non-stop chatting and exchange of ideas, now pretty exhausted π
