It's been a great few days bringing together the CoDiet consortium to discuss progress and exciting plans for the year ahead! Thank you to AZTI for hosting our first annual meeting, and to everyone who came and made the meeting such a success

The CoDiet consortium came together in Bilbao, Spain for the project's first Annual Meeting 🍎 Read all about it: bit.ly/4bLLIfp

Congratulations to Donghee for your 2024 LREC-COLING paper CookingSense! If you like NLP and cooking, this paper is for you 😁 arxiv.org/abs/2405.00523

We feel like we're only just recovering from an exciting and jam-packed weekend at #ExRdFest 🤖🍎🕺 Thank you to everyone who stopped by to meet RoboChef and learn a bit about the CoDiet project! Read more about our time at the festival: bit.ly/4c9TrDN

We are recruiting for a PhD student to work on foundation language models from electronic health records. Project is part of @AI4HealthCentre and Imperial College London, co-supervised with Aldo Faisal, to start Oct 2024. Ideally Home/UK applicant. #NLProc ai4health.io/apply/

Excited to share that my paper has been accepted as an Applied Research paper at #CIKM2024! 🎉 linkedin.com/posts/dongheec…

arxiv.org/abs/2411.01996 This is a cool paper with Imperial! The paper investigates the culinary creativity of LLMs, and whether they can transfer elements of one cuisine to another! 🌮🍕🍱🍲 Congratulations to the authors

Do LLMs need rationales for learning from mistakes? 🤔 When LLMs learn from previous incorrect answers, they typically observe corrective rationales explaining each mistake. In our new preprint, we find these rationales do not help, in fact they hurt performance! 🧵

Can't wait to see everyone at ICLR and NAACL! Check out some of our awesome papers. Come and say hi, we'd love to have a chat :)

Thanks Choi Dong Hee (far left in picture) for your great presentation on your last day here at Imperial! Been brilliant having you here, and looking forward to following your work in the future :)

We have a new paper up on arXiv! 🥳🪇 The paper tries to improve the robustness of closed-source LLMs fine-tuned on NLI, assuming a realistic training budget of 10k training examples. Here's a 60 second rundown of what we found!

Our Imperial NLP community is ready for #EMNLP2025 ✈️ Check out the papers we’ll be presenting next week in Suzhou and come say hi!

Excited to share that my paper has been accepted as an Applied Research paper at #CIKM2025! 🎉 linkedin.com/posts/jinkyu-k…