paper-with-me

홈 › Papers

Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck

2024-04-11 · Nathan Godey, Éric de la Clergerie, Benoît Sagot

Recent advances in language modeling consist in pretraining highly parameterized neural networks on extremely large web-mined text corpora. Training and inference with such models can be costly in practice, which incentivizes the use of smaller counterparts. However, it has been observed that smaller models can suffer from saturation, characterized as a drop in performance at some advanced point in training followed by a plateau. In this paper, we find that such saturation can be explained by a mismatch between the hidden dimension of smaller models and the high rank of the target contextual probability distribution. This mismatch affects the performance of the linear prediction head used in such models through the well-known softmax bottleneck phenomenon. We measure the effect of the softmax bottleneck in various settings and find that models based on less than 1000 hidden dimensions tend to adopt degenerate latent representations in late pretraining, which leads to reduced evaluation performance.

📄 PDF Abstract BibTeX arXiv:2404.07647

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Probing the Limits of Stylistic Alignment in Vision-Language Models

2025-09-29 · Asma Farajidizaji, Akash Gupta, Vatsal Raina arxiv

Vision-language models are increasingly used to generate image captions in specific styles, such as humor or romantic. However, these transformer-based models often struggle with this subjective task in a zero-shot setti…

Synthetic Document Question Answering in Hungarian

2025-05-29 · Jonathan Li, Zoltan Csaki, Nidhi Hiremath, Etash Guha 외

Modern VLMs have achieved near-saturation accuracy in English document visual question-answering (VQA). However, this task remains challenging in lower resource languages due to a dearth of suitable training and evaluati…

Optical Character Recognition (OCR)Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language

2024-09-30 · Vincent Beliveau, Helene Kaas, Martin Prener, Claes N. Ladefoged 외

Natural language processing (NLP) in the medical domain can underperform in real-world applications involving small datasets in a non-English language with few labeled samples and imbalanced classes. There is yet no cons…

Few-Shot LearningSentencetext-classificationText Classification

Toward Inference-optimal Mixture-of-Expert Large Language Models

2024-04-03 · Longfei Yun, Yonghao Zhuang, Yao Fu, Eric P Xing 외

Mixture-of-Expert (MoE) based large language models (LLMs), such as the recent Mixtral and DeepSeek-MoE, have shown great promise in scaling model size without suffering from the quadratic growth of training cost of dens…

On the Difference of BERT-style and CLIP-style Text Encoders

2023-06-06 · Zhihong Chen, Guiming Hardy Chen, Shizhe Diao, Xiang Wan 외

Masked language modeling (MLM) has been one of the most popular pretraining recipes in natural language processing, e.g., BERT, one of the representative models. Recently, contrastive language-image pretraining (CLIP) ha…

Image GenerationLanguage ModelingLanguage ModellingMasked Language Modeling+2