English
Related papers

Related papers: Why do small language models underperform? Studyin…

200 papers

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

Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more…

Computation and Language · Computer Science 2018-06-20 Patrick H. Chen , Si Si , Yang Li , Ciprian Chelba , Cho-jui Hsieh

The rapid advancement of large language models (LLMs) has led to significant improvements in natural language processing but also poses challenges due to their high computational and energy demands. This paper introduces a series of…

Computation and Language · Computer Science 2024-06-27 Dylan Hillier , Leon Guertler , Cheston Tan , Palaash Agrawal , Chen Ruirui , Bobby Cheng

Large language models are pre-trained on ever-growing token budgets under the assumption that better pre-training performance translates to improved downstream models. In this work, we challenge this assumption and show that extended…

Computation and Language · Computer Science 2025-03-31 Jacob Mitchell Springer , Sachin Goyal , Kaiyue Wen , Tanishq Kumar , Xiang Yue , Sadhika Malladi , Graham Neubig , Aditi Raghunathan

Diffusion Transformers have achieved state-of-the-art performance in class-conditional and multimodal generation, yet the structure of their learned conditional embeddings remains poorly understood. In this work, we present the first…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Trung X. Pham , Kang Zhang , Ji Woo Hong , Chang D. Yoo

We introduce adaptive input representations for neural language modeling which extend the adaptive softmax of Grave et al. (2017) to input representations of variable capacity. There are several choices on how to factorize the input and…

Computation and Language · Computer Science 2019-02-26 Alexei Baevski , Michael Auli

The impact of subword tokenization on language model performance is well-documented for perplexity, with finer granularity consistently reducing this intrinsic metric. However, research on how different tokenization schemes affect a model's…

Computation and Language · Computer Science 2025-08-12 Nishant Luitel , Nirajan Bekoju , Anand Kumar Sah , Subarna Shakya

The maximum element of the vector output by the Softmax function approaches zero as the input vector size increases. Transformer-based language models rely on Softmax to compute attention scores, causing the attention distribution to…

Computation and Language · Computer Science 2025-02-03 Ken M. Nakanishi

It is often remarked that neural networks fail to increase their uncertainty when predicting on data far from the training distribution. Yet naively using softmax confidence as a proxy for uncertainty achieves modest success in tasks…

Machine Learning · Computer Science 2021-06-10 Tim Pearce , Alexandra Brintrup , Jun Zhu

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…

Machine Learning · Computer Science 2016-09-20 Alexandre de Brébisson , Pascal Vincent

While recent studies have looked into the abilities of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc, there have been few studies looking into the…

Computation and Language · Computer Science 2023-10-24 Jiao Sun , Yufei Tian , Wangchunshu Zhou , Nan Xu , Qian Hu , Rahul Gupta , John Frederick Wieting , Nanyun Peng , Xuezhe Ma

Low-resource languages (LRLs) face significant challenges in natural language processing (NLP) due to limited data. While current state-of-the-art large language models (LLMs) still struggle with LRLs, smaller multilingual models (mLMs)…

Computation and Language · Computer Science 2025-02-17 Daniil Gurgurov , Ivan Vykopal , Josef van Genabith , Simon Ostermann

Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs. To better understand LLM scaling, we study representational differences between LLMs and…

Large language models often achieve strong benchmark gains without corresponding improvements in broader capability. We hypothesize that this discrepancy arises from differences in training regimes induced by data distribution. To…

Machine Learning · Computer Science 2026-04-10 Hongjian Zou , Yidan Wang , Qi Ding , Yixuan Liao , Xiaoxin Chen

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

Computation and Language · Computer Science 2022-06-20 Michal Štefánik

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention…

Machine Learning · Computer Science 2025-10-07 Ruoxi Yu , Haotian Jiang , Jingpu Cheng , Penghao Yu , Qianxiao Li , Zhong Li

Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary, a process inherently sensitive to typographical errors, length variations, and largely oblivious to the internal structure of…

Computation and Language · Computer Science 2024-10-07 Yekun Chai , Yewei Fang , Qiwei Peng , Xuhong Li

In this work we explore recent advances in Recurrent Neural Networks for large scale Language Modeling, a task central to language understanding. We extend current models to deal with two key challenges present in this task: corpora and…

Computation and Language · Computer Science 2016-02-15 Rafal Jozefowicz , Oriol Vinyals , Mike Schuster , Noam Shazeer , Yonghui Wu

Semantic leakage is a phenomenon recently introduced by Gonen et al. (2024). It refers to a situation in which associations learnt from the training data emerge in language model generations in an unexpected and sometimes undesired way.…

Computation and Language · Computer Science 2025-01-14 Veronika Smilga

Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…

Computation and Language · Computer Science 2026-03-26 Avni Mittal