Large language models show strong cross‑lingual abilities, but previous studies have examined them only at isolated training points. This work pretrains a 1.7B multilingual model on nine languages, recording checkpoints at fine granularity to track translation development. Using word‑level translation and a new dataset, the authors find that early learning is dominated by token‑level copying and surface similarities, while later stages involve more general translation mechanisms and refined copying.
By Felicia K\"orner, Maria Matveev, Florian Eichin, Gitta Kutyniok, Barbara Plank, Michael A. Hedderich
The paper investigates how learning rate and batch size scale when pretraining dense large language models on English‑prevalent corpora, examining both jointly optimal and marginal evolutions across model capacity and data size. It explores the benefits of a Warmup‑Stable‑Decay learning‑rate schedule, assessing whether optimal hyperparameters transfer between stable and decay phases, and evaluates loss scaling forms that capture interactions between model capacity and dataset size. The study provides a baseline scaling procedure and releases the full set of pretraining runs for future OpenEuroLLM development.
By Niccol\`o Ajroldi, Diana Alexandra Onutu, Haider Al-Tahan, J\"org Franke, Sampo Pyysalo, Jenia Jitsev, Aaron Klein
The study investigates how layer‑wise intervention responses in language models change over the course of pretraining, using single‑block identity bypass across multiple checkpoints and model‑domain combinations. It finds that while depth ordering of responses persists, their magnitudes shift, with nearby checkpoints showing stronger rank correspondence than distant ones and large changes occurring at positions that recur across samples and transfer across evaluation domains. Controlled experiments reveal that these longitudinal changes cannot be explained by a single downstream sensitivity and depend on perturbation strength and direction, indicating that layer sensitivity is structured but dynamic.
By Shengye Tao, Yinzhu Cheng, Haihua Xie
The paper investigates when a language model actually learns task information versus when its readout (unembedding matrix) learns to express that information. Using a new parameter‑trajectory cross‑coding method, the authors find that hidden states can encode task data early in training, but the readout reorganizes only in a narrow window (0.4–1.1% of Pythia’s pretraining). By varying the readout learning rate, they show that faster readout learning reduces the gap between hidden‑state encoding and output expression without affecting final performance.
By Matteo He, William F. Shen, Alex Iacob, Andrej Jovanovic, Xinchi Qiu, Nicholas D. Lane
arXiv:2608.30315v1 Announce Type: new
Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lang...
By Junjie Yao, Liangkai Hang, Zhi-Qin John Xu
arXiv:2610.07168v1 Announce Type: new
Abstract: Representations of translated sentences are similar in the inner layers of multilingual language models -- an observation connected to the platonic rep...
By Darshil Doshi, Wenjie Zhou, Corinna Elena Wegner, Daniel J. Korchinski, Santiago Acevedo, Matthieu Wyart
arXiv:2606. 15327v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have demonstrated strong scaling capacity as alternatives to autoregressive language models.
By Keyue Jiang, Yuxiang Wang, Yanan Zhao, Xiang Yu, Qifang Zhao, Bohan Tang, Baojian Zhou, Yanghua Xiao, Lin Qu, Xiaoxiao Xu
Measuring training data influence consistently across language model pretraining is challenging. It is difficult to select downstream tasks or validation sets representative of a model's general capabilities, and reliance on task performance at intermediate checkpoints complicates comparisons across training.
The study investigates whether phonological traces of a first language persist in neural speech models after switching to a second language, mirroring phenomena observed in international adoptees. Using automatic speech recognition models trained on one language and then abruptly switched to another, researchers found that traces of the first language remained in the lowest, pre‑phonemic layers throughout second‑language training. These traces proved functional, as models with early exposure re‑learned their lost first language 14% faster than naive models, an advantage that vanished when the earliest layers were replaced with those from a non‑adopted model.
By Peter Plantinga, Charlotte Moore, Peter W. Donhauser, Krista Byers-Heinlein, Denise Klein
arXiv:2607. 28274v1 Announce Type: cross Abstract: Modern Greek is a richly inflected language, yet the language models built for it are evaluated mainly on factual knowledge, and no benchmark is dedicated to their inflectional competence.
By Ioakeim Perros, Cleopatra Papadopoulou, Ayoub Kirouane, Christos Petrocheilos
arXiv:2606. 00230v1 Announce Type: new Abstract: Grokking, the phenomenon in which neural networks generalize long after fitting their training data, has been studied in supervised settings on many epochs.
By Sherin Muckatira, Namrata Shivagunde, Vijeta Deshpande, Anna Rumshisky
arXiv:2607. 00510v1 Announce Type: new Abstract: Knowing which training examples drive outputs is fundamental to auditing, correcting, and understanding language models, yet for modern LLMs this remains expensive, approximate, and largely post-hoc.
By Dan Ley, Giang Nguyen, Himabindu Lakkaraju, Julius Adebayo