English
Related papers

Related papers: Learning Less Is More: Premature Upper-Layer Atten…

200 papers

Transformers commonly exhibit an attention sink: disproportionately high attention to the first position. We study this behavior in GPT-2-style models with learned query biases and absolute positional embeddings. Combining structural…

Machine Learning · Computer Science 2026-04-17 Yuval Ran-Milo , Hila Ofek , Shahar Mendel

In recent times, BERT-based models have been extremely successful in solving a variety of natural language processing (NLP) tasks such as reading comprehension, natural language inference, sentiment analysis, etc. All BERT-based…

Computation and Language · Computer Science 2023-04-06 Sharath Nittur Sridhar , Anthony Sarah

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Wenjin Ke , Zhe Li , Dong Li , Lu Tian , Emad Barsoum

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Computation and Language · Computer Science 2024-11-11 Mansi Sakarvadia

Advances in language modeling have led to the development of deep attention-based models that are performant across a wide variety of natural language processing (NLP) problems. These language models are typified by a pre-training process…

Human-Computer Interaction · Computer Science 2020-09-16 Joseph F DeRose , Jiayao Wang , Matthew Berger

In recent years, large pre-trained Transformer-based language models have led to dramatic improvements in many natural language understanding tasks. To train these models with increasing sizes, many neural network practitioners attempt to…

Machine Learning · Computer Science 2022-02-01 Minjia Zhang , Niranjan Uma Naresh , Yuxiong He

Transformer models have emerged as fundamental tools across various scientific and engineering disciplines, owing to their outstanding performance in diverse applications. Despite this empirical success, the theoretical foundations of…

Machine Learning · Computer Science 2026-04-14 Zhen Qin , Jinxin Zhou , Jiachen Jiang , Zhihui Zhu

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

The effect of regularizers such as weight decay when training deep neural networks is not well understood. We study the influence of weight decay as well as $L2$-regularization when training neural network models in which parameter matrices…

Machine Learning · Computer Science 2024-11-01 Seijin Kobayashi , Yassir Akram , Johannes Von Oswald

Transformer architecture has shown impressive performance in multiple research domains and has become the backbone of many neural network models. However, there is limited understanding on how it works. In particular, with a simple…

Computation and Language · Computer Science 2023-10-31 Yuandong Tian , Yiping Wang , Beidi Chen , Simon Du

Training deep neural networks in low rank, i.e. with factorised layers, is of particular interest to the community: it offers efficiency over unfactorised training in terms of both memory consumption and training time. Prior work has…

Machine Learning · Computer Science 2022-09-28 Siddhartha Rao Kamalakara , Acyr Locatelli , Bharat Venkitesh , Jimmy Ba , Yarin Gal , Aidan N. Gomez

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due…

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

Computation and Language · Computer Science 2023-02-09 Hongqiu Wu , Ruixue Ding , Hai Zhao , Pengjun Xie , Fei Huang , Min Zhang

Neural NLP models are often miscalibrated and overconfident, assigning high confidence to incorrect predictions and failing to express uncertainty during internal evidence aggregation. This undermines selective prediction and high-stakes…

Artificial Intelligence · Computer Science 2026-03-11 Elias Hossain , Shubhashis Roy Dipta , Subash Neupane , Rajib Rana , Ravid Shwartz-Ziv , Ivan Garibay , Niloofar Yousefi

Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Yuncheng Yang , Chuyan Zhang , Zuopeng Yang , Yuting Gao , Yulei Qin , Ke Li , Xing Sun , Jie Yang , Yun Gu

LLMs' performance on complex tasks is still unsatisfactory. A key issue is that presently LLMs learn in a data-driven schema, while the instructions about these complex tasks are both scarce and hard to collect or construct. On the…

Machine Learning · Computer Science 2024-10-21 Yang Zhao , Li Du , Xiao Ding , Kai Xiong , Ting Liu , Bing Qin

As large language models continue to scale, low-bit weight-only post-training quantization (PTQ) offers a practical solution to their memory-efficient deployment. Although block-wise PTQ is capable of matching the full-precision (FP)…

Artificial Intelligence · Computer Science 2026-05-29 Jung Hyun Lee , June Yong Yang , Jungwook Choi , Eunho Yang

Continual pretraining is a popular way of building a domain-specific pretrained language model from a general-domain language model. In spite of its high efficiency, continual pretraining suffers from catastrophic forgetting, which may harm…

Computation and Language · Computer Science 2024-02-09 Yongyu Yan , Kui Xue , Xiaoming Shi , Qi Ye , Jingping Liu , Tong Ruan