Thomas Jiralerspong Work led by Jin Hwa Lee and Thomas Jiralerspong , with Jade Yu and Yoshua Bengio Updated preprint: arxiv.org/abs/2410.01444

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

Mechanistic understanding of systematic failures in language models is something more research should strive for IMO. This is really interesting work in that vein by Ziling Cheng @ ACL 2025, highly recommend you check it out.

🚨 70 million US workers are about to face their biggest workplace transmission due to AI agents. But nobody asks them what they want. While AI races to automate everything, we took a different approach: auditing what workers want vs. what AI can do across the US workforce.🧵

Two kinds of mindset

Life update: I’m excited to share that I’ll be starting as faculty at the Max Planck Institute for Software Systems(Max Planck Institute for Software Systems) this Fall!🎉 I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html

If you’re in Vienna for ACL go check out our interpretability poster on how feature interactions reflect linguistic structure! Wednesday, 11-12:30, Poster Session #4 (Session 12: IP-Posters), Hall 4/5

We all agree that AI models/agents should augment humans instead of replace us in many cases. But how do we pick when to have AI collaborators, and how do we build them? Come check out our #ACL2025NLP tutorial on Human-AI Collaboration w/ Diyi Yang Joseph Chee Chang, 📍7/27 9am@ Hall N!

⏰ Sharing our work on calibrated confidence scores at #ACL2025NLP, July 29 – 4PM Vienna time (Virtual)! 📰 Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution’s Characteristics aclanthology.org/2025.acl-short… Ori Ernst McGill NLP

How can we use models of cognition to help LLMs interpret figurative language (irony, hyperbole) in a more human-like manner? Come to our #ACL2025NLP poster on Wednesday at 11AM (exhibit hall - exact location TBA) to find out! McGill NLP Mila - Institut québécois d'IA ACL 2025

What do systematic hallucinations in LLMs tell us about their generalization abilities? Come to our poster at #ACL2025 on July 29th at 4 PM in Level 0, Halls X4/X5. Would love to chat about interpretability, hallucinations, and reasoning :) McGill NLP Mila - Institut québécois d'IA ACL 2025

a lot of wisdom in *maybe* house cleaning