I have multiple MSc/PhD openings in my lab at @UBC_CS! Come discover the hidden capabilities/limits of LLMs, e.g. how to learn from, guide, and understand the outputs of models. See my website (bio) for more details. https://t.co/GWEH8yOO2k Apply by December 15th! Also...

Considering a PhD/MSc in NLP? I’m hiring students this cycle! If you are passionate about making language models reliable and safe, eager about understanding and controlling language models, and would like to add to your research some multilingual flavor - apply to my group! 👇

The top places in all of our leaderboards have been cracked. The reign of AI is over.

UBC Computer Science invites applications for up to two full-time tenure-track positions with the following priority areas: visualization, robotics, reinforcement learning, data management, and data mining. Applications are due Wed Dec 10, 2025. https://t.co/ARgHUbnGny

𝑵𝒆𝒘 𝒃𝒍𝒐𝒈𝒑𝒐𝒔𝒕! In which I give some brief reflections on #COLM2025 and give a rundown of a few great papers I checked out!

🤖➡️📉 Post-training made LLMs better at chat and reasoning—but worse at distributional alignment, diversity, and sometimes even steering(!) We measure this with our new resource (Spectrum Suite) and introduce Spectrum Tuning (method) to bring them back into our models! 🌈 1/🧵

New paper: You can make ChatGPT 2x as creative with one sentence. Ever notice how LLMs all sound the same? They know 100+ jokes but only ever tell one. Every blog intro: "In today's digital landscape..." We figured out why – and how to unlock the rest 🔓 Copy-paste prompt: 🧵

Want to hear some hot takes about the future of language modeling, and share your takes too? Stop by the Visions of Language Modeling workshop at COLM on Friday, October 10 in room 519A! There will be over a dozen speakers working on all kinds of problems in modeling language and

Check out @eunjeong_hwang’s paper—how do we give LLMs aspects of social intelligence that actually *help* in conversation?

I considered myself a pretty effective email writer until we (led by the amazing @divingwithorcas!) started building this game. See if you fare any better than I did...

testing a game we're building where the mechanic is writing tricky HR emails, and noticing that LLMs have a built-in secret handshake with users to bypass safety guardrails. This seems both necessary to make LLMs actually useful and like they make guardrails essentially useless

🧵 Academic job market season is almost here! There's so much rarely discussed—nutrition, mental and physical health, uncertainty, and more. I'm sharing my statements, essential blogs, and personal lessons here, with more to come in the upcoming weeks! ⬇️ (1/N)

the economist published my little letter about the necessity of chaos for discovery

Prompting is our most successful tool for exploring LLMs, but the term evokes eye-rolls and grimaces from scientists. Why? Because prompting as scientific inquiry has become conflated with prompt engineering. This is holding us back. 🧵and new paper:

What happens when an LLM is asked to use information that contradicts its knowledge? We explore knowledge conflict in a new preprint📑 TLDR: Performance drops, and this could affect the overall performance of LLMs in model-based evaluation.📑🧵⬇️ 1/8 #NLProc #LLM #AIResearch

The fact that in pretty much all LLMs the generative branching factor goes down as the model keeps generating feels like a fundamental limit of LLM creativity, and I've never seen a satisfying solution.

LLMs excel at finding surprising “needles” in very long documents, but can they detect when information is conspicuously missing? 🫥AbsenceBench🫥 shows that even SoTA LLMs struggle on this task, suggesting that LLMs have trouble perceiving “negative space” in documents. paper:

𝐖𝐡𝐚𝐭 𝐇𝐚𝐬 𝐁𝐞𝐞𝐧 𝐋𝐨𝐬𝐭 𝐖𝐢𝐭𝐡 𝐒𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐄𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧? I'm happy to announce that the preprint release of my first project is online! Developed with the amazing support of @lasha_nlp and @anmarasovic (Full link below 👇)

Data curation is crucial for LLM reasoning, but how do we know if our dataset is not overfit to one benchmark and generalizes to unseen distributions? 🤔 𝐃𝐚𝐭𝐚 𝐝𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 is key, when measured correct—it strongly predicts model generalization in reasoning tasks! 🧵

Your language model is wasting half of its layers to just refine probability distributions rather than doing interesting computations. In our paper, we found that the second half of the layers of the Llama 3 models have minimal effect on future computations. 1/6

Many agents (Claude Code, Codex CLI) interact with the terminal to do valuable tasks, but do they currently work well enough to deploy en masse? We’re excited to introduce Terminal-Bench: An evaluation environment and benchmark for AI agents on real-world terminal tasks. Tl;dr