Imperial NLP @ACL25 ✈️
@imperial_nlp
We are the Natural Language Processing community at @imperialcollege. BFF with @EdinburghNLP
ACL is almost here 🎉 Our Imperial NLP community will be presenting several papers at the conference next week. We look forward to seeing everyone in Vienna!
I’ll be at #acl2025 next week in Vienna🇦🇹 presenting our work. Looking forward to meeting old and new friends! If you like to discuss chatbot, code generation, multi-agents, robustness, hate speech detection, or just life😆, feel free to reach out and I’d love to chat!
🙌Happy to share our paper, “DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising” is accepted to #ACL2025! Great thanks to my co-authors Huichi Zhou, @MarekRei, @lspecia! Arxiv: arxiv.org/abs/2407.00248 GitHub: github.com/Nickeilf/Diffu…
I've had an amazing time on my US summer tour, thanks to all the universities for hosting me! If you'd like to see my talk about all my PhD research, check out the link in the message below 👇👇 It's fun to watch because you can see just how much I love presenting 🙂🙂
Who else is going to #ACL in Vienna? I look forward to catching up with old friends as well as meeting new ones, especially if you are interested in #XAI, #CoT, #Alignment, #SafeAI. I will also be giving a talk at the FEVER Workshop, more on this soon!
Presenting two papers at the MemFM workshop at ICML! Both touch upon how near duplicates (and beyond) in LLM training data contribute to memorization. - arxiv.org/pdf/2405.15523 - arxiv.org/pdf/2506.20481 @_igorshilov @yvesalexandre
Lovely place for a conference! Come see my poster on privacy auditing of synthetic text data at 11am today! East Exhibition Hall A-B #E-2709
(1/9) LLMs can regurgitate memorized training data when prompted adversarially. But what if you *only* have access to synthetic data generated by an LLM? In our @icmlconf paper, we audit how much information synthetic data leaks about its private training data 🐦🌬️
Will be at @icmlconf in Vancouver next week! 🇨🇦 Will be presenting our poster on privacy auditing of synthetic text. Presentation here icml.cc/virtual/2025/p… And will also be presenting two papers at the MemFM workshop! icml2025memfm.github.io Hit me up if you want to chat!
(1/9) LLMs can regurgitate memorized training data when prompted adversarially. But what if you *only* have access to synthetic data generated by an LLM? In our @icmlconf paper, we audit how much information synthetic data leaks about its private training data 🐦🌬️
we have similar ideas to train EBMs, but focus on discrete cases of set function learning 😄 check our neurips 2022 oral paper (section 3.1): arxiv.org/abs/2203.01693
Energy-Based Transformers are Scalable Learners and Thinkers
Check out our recent work on prompt injection attacks! Tl;DR: aligned LLMs show to defend against prompt injection; yet with a strong attacker (GCG on steroids), we find that successful attacks (almost) always exist, but are just harder to find. arxiv.org/pdf/2505.15738
Have you ever uploaded a PDF 📄 to ChatGPT 🤖 and asked for a summary? There is a chance the model followed hidden instructions inside the file instead of your prompt 😈 A thread 🧵
Welcome to @imperialcollege @oanacamb 🎉
🥳Thrilled to announce that I started as an Assistant Professor @imperialcollege! Grateful to all my mentors and collaborators from @ucl, @UniofOxford, and worldwide! I will continue working on 🌟Alignment and A(G)I Safety🌟 and 🚨 I have funding for PhD students 🚨. I look…
(1/9) LLMs can regurgitate memorized training data when prompted adversarially. But what if you *only* have access to synthetic data generated by an LLM? In our @icmlconf paper, we audit how much information synthetic data leaks about its private training data 🐦🌬️
How good can privacy attacks against LLM pretraining get if you assume a very strong attacker? Check it out in our preprint ⬇️
Are modern large language models (LLMs) vulnerable to privacy attacks that can determine if given data was used for training? Models and dataset are quite large, what should we even expect? Our new paper looks into this exact question. 🧵 (1/10)
🚨 New preprint alert – accepted at #ACL2025 Findings!🚨
If anyone has done any work improving the robustness of NLI models and we didn't cite you in our appendix, please share a link to your work - I would love to include it Our appendix related work on NLI robustness is a bit of a monster 😅🧌 x.com/_joestacey_/st…
This work was really fun and a great last paper for my PhD. Check it out 🙂 arxiv.org/abs/2505.20209 P.S. if you know about a paper improving NLI model robustness not already in our related work appendix, I would love to hear about it🥰
If you're interested in NLI or model robustness, this is a nice and fun paper - check it out 🙂 x.com/_joestacey_/st…
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!
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!
🙌Happy to share our paper, “DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising” is accepted to #ACL2025! Great thanks to my co-authors Huichi Zhou, @MarekRei, @lspecia! Arxiv: arxiv.org/abs/2407.00248 GitHub: github.com/Nickeilf/Diffu…
Thrilled to share our new preprint on Reinforcement Learning for Reverse Engineering (RLRE) 🚀 We demonstrate that human preferences can be reverse engineered effectively by pipelining LLMs to optimise upstream preambles via reinforcement learning 🧵⬇️