LLM developers train their models to follow prosocial values, but post-training can influence model behavior in unexpected ways. In our new paper "Predicting Alignment Generalization with Value Representations", we ask how well downstream effects of value alignment can be predicted in advance.

🚨New Paper!🚨 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 uncertainty… 🧵(1/10)

Our new paper in #PNAS (bit.ly/4fcWfma) presents a surprising finding—when words change meaning, older speakers rapidly adopt the new usage; inter-generational differences are often minor. w/ Michelle Yang, ‪@sivareddyg.bsky.social‬ , @msonderegger.bsky.social‬ and @dallascard.bsky.social‬👇(1/12)

Huge congratulations to Dr. @vernadankers.bsky.social for passing her viva today! 🥳🎓 It's truly been an honour sharing the PhD journey with you. I wasn’t ready for the void your sudden departure left (in the office and in my life!). Your new colleagues are lucky to have you! 🥺🥰

A blizzard is raging through Montreal when your friend says “Looks like Florida out there!” Humans easily interpret irony, while LLMs struggle with it. We propose a 𝘳𝘩𝘦𝘵𝘰𝘳𝘪𝘤𝘢𝘭-𝘴𝘵𝘳𝘢𝘵𝘦𝘨𝘺-𝘢𝘸𝘢𝘳𝘦 probabilistic framework as a solution. Paper: arxiv.org/abs/2506.09301 to appear @ #ACL2025 (Main)

I guess that now that I have 1% of my Twitter followers follow me here 😅, 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

🔔 Reminder & Call for #VLMs4All @ #CVPR2025! Help shape the future of culturally aware & geo-diverse VLMs: ⚔️ Challenges: Deadline: Apr 15 🔗https://sites.google.com/view/vlms4all/challenges 📄 Papers (4pg): Deadline: Apr 22 🔗https://sites.google.com/view/vlms4all/call-for-papers Join us!

MAPS - CVPR 2026 Workshop@mapscvpr.bsky.social · 2y ago

📢Excited to announce our upcoming workshop - Vision Language Models For All: Building Geo-Diverse and Culturally Aware Vision-Language Models (VLMs-4-All) @CVPR 2025! 🌐 sites.google.com/view/vlms4all

Our DeepSeek-R1 'Thoughtology' paper 🧠💡brings a wealth of interesting insights into analyzing reasoning chains and across a variety of tasks. Check it out! mcgill-nlp.github.io/thoughtology/

DeepSeek-R1 Thoughtology: Let’s think about LLM reasoning

Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an answer for a given input, DeepSeek-R1 creates detailed multi-st...

mcgill-nlp.github.io

Sara Vera Marjanovic@saravera.bsky.social · 2y ago

Models like DeepSeek-R1 🐋 mark a fundamental shift in how LLMs approach complex problems. In our preprint on R1 Thoughtology, we study R1’s reasoning chains across a variety of tasks; investigating its capabilities, limitations, and behaviour. 🔗: mcgill-nlp.github.io/thoughtology/

🚀 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. 🌍🔥 #CVPR2025 #VLMs4All2025

MAPS - CVPR 2026 Workshop@mapscvpr.bsky.social · 2y ago

📢Excited to announce our upcoming workshop - Vision Language Models For All: Building Geo-Diverse and Culturally Aware Vision-Language Models (VLMs-4-All) @CVPR 2025! 🌐 sites.google.com/view/vlms4all

Instruction-following retrievers can efficiently and accurately search for harmful and sensitive information on the internet! 🌐💣 Retrievers need to be aligned too! 🚨🚨🚨 Work done with the wonderful Nick and @sivareddyg.bsky.social 🔗 mcgill-nlp.github.io/malicious-ir/ Thread: 🧵👇

🚨🚨🚨 Checkout our new position paper on rethinking LLM alignment through social, economic, and contractual frameworks! 🌍💼⚖️ Full paper: arxiv.org/abs/2503.00069 How should AI align with society? Let’s discuss!👇

Karolina Stańczak@karstanczak.bsky.social · 2y ago

📢New Paper Alert!🚀 Human alignment balances social expectations, economic incentives, and legal frameworks. What if LLM alignment worked the same way?🤔 Our latest work explores how social, economic, and contractual alignment can address incomplete contracts in LLM alignment🧵

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 😅

Benno Krojer@bennokrojer.bsky.social · 2y ago

AURORA 🌌 is now accepted as a Spotlight at NeurIPS 🥂 We wondered if a model can do *controlled* video generation but in a *single* step? So we built a dataset+model for “taking actions” on images via editing, or what you could call single-step controlled video gen