📜Preprint out! arxiv.org/abs/2407.03181 We propose to fine-tune LLMs to generate diverse chains of thought (DCoT) in a single inference step. This enables within-inference refinement of the cots, no external feedback needed!

We see news like this from time to time and that’s why it’s vital to keep researching on tools to prove these cases! Our #NAACL2025 paper shows that with over 10k tokens, we can reliably detect whether a text was part of an LLM’s training data aclanthology.org/2025.findings-…

Leaky Thoughts Hey AI devs, be careful how you prompt reasoning models. This work shows that reasoning traces frequently contain sensitive user data. More of my notes below:

🎉 Very excited to see our new Leaky Thoughts 🫗 paper featured among last week's top AI papers by both DAIR.AI and The AI Timeline! - x.com/dair_ai/status… - x.com/TheAITimeline/… ➡️ Learn more about the paper in this great thread by elvis: x.com/omarsar0/statu… ➡️

Excited to share our paper: "Chain-of-Thought Is Not Explainability"! We unpack a critical misconception in AI: models explaining their Chain-of-Thought (CoT) steps aren't necessarily revealing their true reasoning. Spoiler: transparency of CoT can be an illusion. (1/9) 🧵

"in 2025 we will have flying cars" 😂😂😂

On the rankability of visual embeddings Ankit Sonthalia Arnas Uselis Seong Joon Oh tl;dr: one can discover "property ordering axis", such as age, etc in visual descriptors, often by having a couple of extreme examples. arxiv.org/abs/2507.03683

Excited to present Diverse Chains of Thought at #ACL2025NLP Do you have a dataset with more than one CoT/question? Do you want to train with that? Come to our poster to see how to make the most out of your data! 🗓️ Wednesday 30th 🕦11:00 📍Level 1 1.86 underline.io/events/485/pos…

📢🧵 Thread | Celebrating Ibero-American NLP at #ACL2025! 🇪🇸🇵🇹🇲🇽🇨🇴🇧🇷🇦🇷 ... 🌎 The SomosNLP @ACL  community is showing up strong at ACL 2025 ! We want to highlight all the papers from our vibrant community 👇 #NLProc #NLP #IberoAmerica

I’ll be presenting today at 11:00 in hall x5 booth 209 #ACL2025NLP come and let’s talk about how to train with CoTs!

Excited to be part of this work! Congrats all the authors! 🎉 #EMNLP2025 Check the thread from elvis if you want to know more about the privacy risks introduced by the reasoning traces in reasoning models 🤓 x.com/omarsar0/statu…

Friends in Europe working in industry on Generative AI, can you help my friend with this survey. Participation is compensated with $40 / €36 Amazon gift card!