English
Related papers

Related papers: Training Dynamics Underlying Language Model Scalin…

200 papers

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Computation and Language · Computer Science 2023-10-24 Lingyu Gao , Debanjan Ghosh , Kevin Gimpel

A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly understood, and a mechanistic explanation via mathematical…

Machine Learning · Computer Science 2023-11-07 Sanjeev Arora , Anirudh Goyal

Modern language models rely on static vocabularies, fixed before pretraining, in contrast to the adaptive vocabulary acquisition observed in human language learning. To bridge this gap, we introduce vocabulary curriculum learning, an…

Computation and Language · Computer Science 2025-02-26 Fangyuan Yu

Language Models (LMs) struggle with linguistic understanding at the discourse level, even though discourse patterns such as coherence, cohesion, and narrative flow are prevalent in their pre-training data. To improve the discourse…

Computation and Language · Computer Science 2026-02-17 Zachary Bamberger , Ofek Glick , Chaim Baskin , Yonatan Belinkov

Massively Multilingual Language Models (MMLMs) have recently gained popularity due to their surprising effectiveness in cross-lingual transfer. While there has been much work in evaluating these models for their performance on a variety of…

Computation and Language · Computer Science 2022-10-25 Kabir Ahuja , Sunayana Sitaram , Sandipan Dandapat , Monojit Choudhury

Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger. How do language models of different sizes learn during pre-training? Why do larger…

Computation and Language · Computer Science 2023-05-31 Mengzhou Xia , Mikel Artetxe , Chunting Zhou , Xi Victoria Lin , Ramakanth Pasunuru , Danqi Chen , Luke Zettlemoyer , Ves Stoyanov

Pure speech language models aim to learn language directly from raw audio without textual resources. A key challenge is that discrete tokens from self-supervised speech encoders result in excessively long sequences, motivating recent work…

Computation and Language · Computer Science 2026-02-18 Nicol Visser , Simon Malan , Danel Slabbert , Herman Kamper

Large Language Models (LLMs) are large-scale pretrained models that have achieved remarkable success across diverse domains. These successes have been driven by unprecedented complexity and scale in both data and computations. However, due…

Zero-shot Learning (ZSL), which aims to predict for those classes that have never appeared in the training data, has arisen hot research interests. The key of implementing ZSL is to leverage the prior knowledge of classes which builds the…

Artificial Intelligence · Computer Science 2021-02-16 Yuxia Geng , Jiaoyan Chen , Zhuo Chen , Jeff Z. Pan , Zhiquan Ye , Zonggang Yuan , Yantao Jia , Huajun Chen

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…

Computation and Language · Computer Science 2026-03-20 Asmita Bhardwaj , Yuya Jeremy Ong , Eelaaf Zahid , Basel Shbita

How well do text-only large language models (LLMs) align with the visual world? We present a systematic evaluation of this question by incorporating frozen representations of various language models into a discriminative vision-language…

Computation and Language · Computer Science 2026-01-19 Jona Ruthardt , Gertjan J. Burghouts , Serge Belongie , Yuki M. Asano

Zero-Shot Learning (ZSL) presents the challenge of identifying categories not seen during training. This task is crucial in domains where it is costly, prohibited, or simply not feasible to collect training data. ZSL depends on a mapping…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 William Heyden , Habib Ullah , M. Salman Siddiqui , Fadi Al Machot

Large language models (LLMs) often struggle to learn from corrective feedback within a conversational context. They are rarely proactive in soliciting this feedback, even when faced with ambiguity, which can make their dialogues feel…

Computation and Language · Computer Science 2026-02-19 Jonathan Cook , Diego Antognini , Martin Klissarov , Claudiu Musat , Edward Grefenstette

Using Large Language Models (LLMs) in real-world applications presents significant challenges, particularly in balancing computational efficiency with model performance. Optimizing acceleration after fine-tuning and during inference is…

Computation and Language · Computer Science 2025-09-09 Sajjad Kachuee , Mohammad Sharifkhani

Zero-shot In-context learning is the phenomenon where models can perform the task simply given the instructions. However, pre-trained large language models are known to be poorly calibrated for this task. One of the most effective…

Computation and Language · Computer Science 2024-04-04 Suzanna Sia , Alexandra DeLucia , Kevin Duh

Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this…

Computation and Language · Computer Science 2024-10-07 Ernie Chang , Matteo Paltenghi , Yang Li , Pin-Jie Lin , Changsheng Zhao , Patrick Huber , Zechun Liu , Rastislav Rabatin , Yangyang Shi , Vikas Chandra

Zero-Shot Learning (ZSL) is an emerging research that aims to solve the classification problems with very few training data. The present works on ZSL mainly focus on the mapping of learning semantic space to visual space. It encounters many…

Computer Vision and Pattern Recognition · Computer Science 2021-03-01 Zeng Ting , Xiang Hongxin , Xie Cheng , Yang Yun , Liu Qing

Modern LLM pre-training consumes vast amounts of compute and training data, making the scaling behavior, or scaling laws, of different models a key distinguishing factor. Discrete diffusion language models (DLMs) have been proposed as an…

Machine Learning · Computer Science 2026-02-17 Dimitri von Rütte , Janis Fluri , Omead Pooladzandi , Bernhard Schölkopf , Thomas Hofmann , Antonio Orvieto

Model depth is a double-edged sword in deep learning: deeper models achieve higher accuracy but require higher computational cost. To efficiently train models at scale, an effective strategy is the progressive training, which scales up…

Machine Learning · Computer Science 2025-11-10 Zhiqi Bu

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…