McGill NLP
@mcgill-nlp.bsky.social
Reposted by McGill NLP
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)
Paper: arxiv.org/abs/2506.09301 to appear @ #ACL2025 (Main)
June 26, 2025 at 3:52 PM
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)
Paper: arxiv.org/abs/2506.09301 to appear @ #ACL2025 (Main)
Reposted by McGill NLP
"Build the web for agents, not agents for the web"
This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).
arxiv.org/abs/2506.10953
This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).
arxiv.org/abs/2506.10953
June 14, 2025 at 4:17 AM
"Build the web for agents, not agents for the web"
This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).
arxiv.org/abs/2506.10953
This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).
arxiv.org/abs/2506.10953
Reposted by McGill NLP
Excited to share the results of my recent internship!
We ask 🤔
What subtle shortcuts are VideoLLMs taking on spatio-temporal questions?
And how can we instead curate shortcut-robust examples at a large-scale?
We release: MVPBench
Details 👇🔬
We ask 🤔
What subtle shortcuts are VideoLLMs taking on spatio-temporal questions?
And how can we instead curate shortcut-robust examples at a large-scale?
We release: MVPBench
Details 👇🔬
June 13, 2025 at 2:47 PM
Excited to share the results of my recent internship!
We ask 🤔
What subtle shortcuts are VideoLLMs taking on spatio-temporal questions?
And how can we instead curate shortcut-robust examples at a large-scale?
We release: MVPBench
Details 👇🔬
We ask 🤔
What subtle shortcuts are VideoLLMs taking on spatio-temporal questions?
And how can we instead curate shortcut-robust examples at a large-scale?
We release: MVPBench
Details 👇🔬
Exciting work on hallucinations from @ziling-cheng.bsky.social
Do LLMs hallucinate randomly? Not quite.
Our #ACL2025 (Main) paper shows that hallucinations under irrelevant contexts follow a systematic failure mode — revealing how LLMs generalize using abstract classes + context cues, albeit unreliably.
📎 Paper: arxiv.org/abs/2505.22630 1/n
Our #ACL2025 (Main) paper shows that hallucinations under irrelevant contexts follow a systematic failure mode — revealing how LLMs generalize using abstract classes + context cues, albeit unreliably.
📎 Paper: arxiv.org/abs/2505.22630 1/n
June 6, 2025 at 6:15 PM
Exciting work on hallucinations from @ziling-cheng.bsky.social
Reposted by McGill NLP
Incredibly proud of my students @adadtur.bsky.social and Gaurav Kamath for winning a SAC award at #NAACL2025 for their work on assessing how LLMs model constituent shifts.
May 1, 2025 at 3:11 PM
Incredibly proud of my students @adadtur.bsky.social and Gaurav Kamath for winning a SAC award at #NAACL2025 for their work on assessing how LLMs model constituent shifts.
Reposted by McGill NLP
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
May 1, 2025 at 2:30 PM
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
Reposted by McGill NLP
Presenting ✨ 𝐂𝐇𝐀𝐒𝐄: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠 𝐬𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐝𝐚𝐭𝐚 𝐟𝐨𝐫 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 ✨
Work w/ fantastic advisors Dima Bahdanau and @sivareddyg.bsky.social
Thread 🧵:
Work w/ fantastic advisors Dima Bahdanau and @sivareddyg.bsky.social
Thread 🧵:
February 21, 2025 at 4:29 PM
Presenting ✨ 𝐂𝐇𝐀𝐒𝐄: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠 𝐬𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐝𝐚𝐭𝐚 𝐟𝐨𝐫 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 ✨
Work w/ fantastic advisors Dima Bahdanau and @sivareddyg.bsky.social
Thread 🧵:
Work w/ fantastic advisors Dima Bahdanau and @sivareddyg.bsky.social
Thread 🧵:
Reposted by McGill NLP
Super excited to finally announce our NAACL 2025 main conference paper “Language Models Largely Exhibit Human-like Constituent Ordering Preferences”!
We examine constituent ordering preferences between humans and LLMs; we present two main findings… 🧵
We examine constituent ordering preferences between humans and LLMs; we present two main findings… 🧵
February 19, 2025 at 7:31 PM
Super excited to finally announce our NAACL 2025 main conference paper “Language Models Largely Exhibit Human-like Constituent Ordering Preferences”!
We examine constituent ordering preferences between humans and LLMs; we present two main findings… 🧵
We examine constituent ordering preferences between humans and LLMs; we present two main findings… 🧵
Reposted by McGill NLP
At McGill we have an NLP lab that works on a lot of things, from human-AI collaboration, to evaluation, to low resource NLP (me).
@emnlpmeeting.bsky.social just happened in Miami, and my colleagues just presented six papers there:
@emnlpmeeting.bsky.social just happened in Miami, and my colleagues just presented six papers there:
Our lab members recently presented 3 papers at @emnlpmeeting.bsky.social in Miami ☀️ 📜
From interpretability to bias/fairness and cultural understanding -> 🧵
From interpretability to bias/fairness and cultural understanding -> 🧵
November 24, 2024 at 4:31 PM
At McGill we have an NLP lab that works on a lot of things, from human-AI collaboration, to evaluation, to low resource NLP (me).
@emnlpmeeting.bsky.social just happened in Miami, and my colleagues just presented six papers there:
@emnlpmeeting.bsky.social just happened in Miami, and my colleagues just presented six papers there:
It turns out we had even more papers at EMNLP!
Let's complete the list with three more🧵
Let's complete the list with three more🧵
Our lab members recently presented 3 papers at @emnlpmeeting.bsky.social in Miami ☀️ 📜
From interpretability to bias/fairness and cultural understanding -> 🧵
From interpretability to bias/fairness and cultural understanding -> 🧵
November 24, 2024 at 2:17 AM
It turns out we had even more papers at EMNLP!
Let's complete the list with three more🧵
Let's complete the list with three more🧵
Our lab members recently presented 3 papers at @emnlpmeeting.bsky.social in Miami ☀️ 📜
From interpretability to bias/fairness and cultural understanding -> 🧵
From interpretability to bias/fairness and cultural understanding -> 🧵
November 23, 2024 at 8:35 PM
Our lab members recently presented 3 papers at @emnlpmeeting.bsky.social in Miami ☀️ 📜
From interpretability to bias/fairness and cultural understanding -> 🧵
From interpretability to bias/fairness and cultural understanding -> 🧵