Imperial NLP

Excited to share our ICLR and NAACL papers! Please come and say hi, we're super friendly :)

Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts Large Language Models (LLMs) possess vast amounts of knowledge within their parameters, prompting research into methods for locating and editing this knowledge. Previous work has largely focused on lo...

Cool paper by Imperial’s Lihu Chen in identifying query-relevant neurons in LLMs for long form texts! arxiv.org/abs/2406.10868

Recently accepted at AAAI 2025 😍

This is a cool paper with Imperial! arxiv.org/abs/2411.01996

The paper investigates the culinary creativity of LLMs, and whether they can transfer elements of one cuisine to another! 🌮🍕🍱🍲

Congratulations to the authors

Meta-Reasoning Improves Tool Use in Large Language Models External tools help large language models (LLMs) succeed at tasks where they would otherwise typically fail. In existing frameworks, LLMs learn tool use either by in-context demonstrations or via full...

Hi Bluesky, would like to introduce myself 🙂

I am PhD-ing at Imperial College under @marekrei.bsky.social’s supervision. I am broadly interested in LLM/LVLM reasoning & planning 🤖 (here’s our latest work arxiv.org/abs/2411.04535)

Do reach out if you are interested in these (or related) topics!

StateAct: State Tracking and Reasoning for Acting and Planning with Large Language Models Planning and acting to solve `real' tasks using large language models (LLMs) in interactive environments has become a new frontier for AI methods. While recent advances allowed LLMs to interact with o...

Quick intro to myself.

I am a CS PhD in LLM Agents @imperial-nlp.bsky.social with @marekrei.bsky.social.

This is our latest work on LLM Agents:

StateAct: arxiv.org/abs/2410.02810 (outperforming ReAct by ~10%).

Feel free to reach out for collaboration.

Creating Interpretable Models with Atomic Inference - Marek Rei This is a guest post from Joe Stacey about our quest to create interpretable Natural Language Inference (NLI) models. In this post he will share…

Now I have like a gazillion new Bluesky followers, posting a link again to a blog post about my #EMNLP2024 and EMNLP 2022 papers. It’s a fun 10 minute read about our ideas on interpretable neural architectures.

❤️ to my fantastic collaborators

www.marekrei.com/blog/creatin...

Welcome to Bluesky to more of our NLP researchers at Imperial!! Looking forward to following everyone's work on here.

To follow us all click 'follow all' in the starter pack below

go.bsky.app/Bv5thAb

Thanks to everyone at #EMNLP2024 from all of us at Imperial. It was a fantastic conference, and we loved meeting you and hearing about your work.

See you at the next conference! 😍

These tips are great! 😍

Great paper Lisa! This new work on tool selection initially uses a fine-tuned LLM to find good candidate tools, before an LLM without fine-tuning reasons over these candidates, with significant performance improvements.

After going to NAACL, ACL and #EMNLP2024 this year, here are a few tips I’ve picked up about attending #NLP conferences.

Would love to hear any other tips if you have them!

This proved very popular on another (more evil) social media platform, so sharing here also 🙂

My 10 tips: