Fact: A lot of Dutch laptops have this special tray to warm up your stroopwafel.

Can #LLMs truly reason over loooong context? 🤔 NoCha asks LLMs to verify claims about *NEW* fictional books 🪄 📚 ⛔ LLMs that solve needle-in-the-haystack (~100%) struggle on NoCha! ⛔ None of 11 tested LLMs reach human performance → 97%. The best, #GPT-4o, gets only 55.8%.

modern LM research seems to be the exact repetition of MT research. here goes the prediction; someone will reinvent minimum Bayes risk decoding but will call it super-aligned, super-reasoning majority voting of galaxy-of-thoughts.

alexandra birch asking the important questions in the #eamt2024 keynote

Next week I'll be in Vienna at ICML Conference! Want to learn more on how to explicitly model embeddings on hypersphere and encourage dispersion during training? Come to the Gram Workshop poster session 2 on 27.07 Shoutout to my collaborators Hua Chang Bakker and timorous bestie 😷 💫

1/4 #ACL2024 Excited to share our new paper on the impact of fine-tuning on the qualitative advantages of LLMs in machine translation! 🤖 Our work highlights the importance of preserving LLM capabilities during fine-tuning. arxiv.org/abs/2405.20089

Come check our poster tomorrow at GRaM Workshop at ICML 2024 ICML Conference if you want to discuss dispersion of text embeddings on hyperspheres! 27.07 at Poster session 2. #ICML2024

Language Technology Lab got four papers accepted for #EMNLP2024! Congrats to authors Kata Naszadi, Shaomu Tan, Baohao Liao Baohao Liao, Di Wu Di Wu 🥳🥳

We show that a grammar book provides little or even no help for translation in LLMs, questioning the recent "truly zero-shot translation" --- no data no gain, still 🧐

Unsloth has identified and fixed the gradient accumulation issue I reported last week. The problem turned out to be more significant than I expected, impacting multi-GPU training as well. This means we’ve likely been training models that didn’t perform as well as they could

Do we like this? arxiv.org/abs/2410.05258

🥪New Paper! 🥪Introducing Byte Latent Transformer (BLT) - A tokenizer free model scales better than BPE based models with better inference efficiency and robustness. 🧵

🎯 ComfyUI-Copilot (AIGC Assistant) is now open-source, brought to you by Alibaba International! 🎉 🍀 Enhance ComfyUI workflow design and optimization with LLM-Agent ✨ Empowering AIGC and exploring Multimodal Agents 🚀 Stay tuned for more features like dynamic parameter

🚨New machine translation dataset alert! 🚨We expanded the language coverage of WMT24 from 9 to 55 en->xx language pairs by collecting new reference translations for 46 languages in a dataset called WMT24++ Paper: arxiv.org/abs/2502.12404… Data: huggingface.co/datasets/googl…

We are happy to announce the second release of HPLT bilingual datasets: - 50 English-centric language pairs = 380M parallel sentences (HPLT) 🤩 - 1,275 non-English-centric language pairs = 16.7B parallel sentences (MultiHPLT) 😮 Available at the HPLT dataset catalogue and OPUS.

Whitespace-ignoring tokenization is an fundamental feature of Sentenepiece, implemented since its early stages (around 2017) Using whitespace yielded better results on MT. It would be helpful if you could mention this. github.com/google/sentenc…

Model Distillation

🔥Exited to share our new work on reproducibility challenges in reasoning models caused by numerical precision. Ever run the same prompt twice and get completely different answers from your LLM under greedy decoding? You're not alone. Most LLMs today default to BF16 precision,

📢 Next week, I will be presenting our paper "Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs" at ACL 2025! Paper: arxiv.org/abs/2505.09338 Blog Post: frankniujc.github.io/publications/a… Talk: youtube.com/watch?v=XcsKon…

Beautiful Google Research paper. LLMs can learn in context from examples in the prompt, can pick up new patterns while answering, yet their stored weights never change. That behavior looks impossible if learning always means gradient descent. The mechanisms through which this