English
Related papers

Related papers: Interpreting Arithmetic Mechanism in Large Languag…

200 papers

Visual explanation enables human to understand the decision making of Deep Convolutional Neural Network (CNN), but it is insufficient to contribute the performance improvement. In this paper, we focus on the attention map for visual…

Computer Vision and Pattern Recognition · Computer Science 2019-04-11 Hiroshi Fukui , Tsubasa Hirakawa , Takayoshi Yamashita , Hironobu Fujiyoshi

Linguistic features have shown promising applications for detecting various cognitive impairments. To improve detection accuracies, increasing the amount of data or the number of linguistic features have been two applicable approaches.…

Computation and Language · Computer Science 2019-03-29 Zining Zhu , Jekaterina Novikova , Frank Rudzicz

While attention has been an increasingly popular component in deep neural networks to both interpret and boost the performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable.…

Computer Vision and Pattern Recognition · Computer Science 2022-04-22 Shi Chen , Ming Jiang , Jinhui Yang , Qi Zhao

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Yanwen Fang , Yuxi Cai , Jintai Chen , Jingyu Zhao , Guangjian Tian , Guodong Li

Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and interpret the learned internal mechanisms that contribute to…

Artificial Intelligence · Computer Science 2018-01-03 Christopher Grimm , Dilip Arumugam , Siddharth Karamcheti , David Abel , Lawson L. S. Wong , Michael L. Littman

Self-attention mechanism in graph neural networks (GNNs) led to state-of-the-art performance on many graph representation learning tasks. Currently, at every layer, attention is computed between connected pairs of nodes and depends solely…

Machine Learning · Computer Science 2021-08-27 Guangtao Wang , Rex Ying , Jing Huang , Jure Leskovec

Attention improves representation learning over RNNs, but its discrete nature limits continuous-time (CT) modeling. We introduce Neuronal Attention Circuit (NAC), a novel, biologically inspired CT-Attention mechanism that reformulates…

Artificial Intelligence · Computer Science 2026-01-07 Waleed Razzaq , Izis Kanjaraway , Yun-Bo Zhao

Large language models (LLMs) have achieved state-of-the-art performance in a variety of tasks, but remain largely opaque in terms of their internal mechanisms. Understanding these mechanisms is crucial to improve their reasoning abilities.…

Neurons and Cognition · Quantitative Biology 2025-12-15 Xueqi Ma , Jun Wang , Yanbei Jiang , Sarah Monazam Erfani , Tongliang Liu , James Bailey

Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploit a multi-channel attention mechanism in feature space. Our…

Computer Vision and Pattern Recognition · Computer Science 2019-05-01 Masanari Kimura , Masayuki Tanaka

In neuroscience, attention has been shown to bidirectionally interact with reinforcement learning (RL) processes. This interaction is thought to support dimensionality reduction of task representations, restricting computations to relevant…

Artificial Intelligence · Computer Science 2020-07-14 Lennart Bramlage , Aurelio Cortese

Large language models (LLMs) exhibit strong multilingual abilities, yet the neural mechanisms behind language-specific processing remain unclear. We analyze language-specific neurons in Llama-3.1-8B, Mistral-Nemo-12B, and Aya-Expanse-8B &…

Computation and Language · Computer Science 2025-11-04 Daniil Gurgurov , Katharina Trinley , Yusser Al Ghussin , Tanja Baeumel , Josef van Genabith , Simon Ostermann

Mathematical reasoning in large language models (LMs) has garnered significant attention in recent work, but there is a limited understanding of how these models process and store information related to arithmetic tasks within their…

Computation and Language · Computer Science 2023-10-23 Alessandro Stolfo , Yonatan Belinkov , Mrinmaya Sachan

Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal,…

Software Engineering · Computer Science 2026-03-20 Zhe Yin , Xiaodong Gu , Beijun Shen

Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations can be safely removed. While attention scores are commonly…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Samyak Jha , Junho Kim

While attention has been an increasingly popular component in deep neural networks to both interpret and boost performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable. In…

Computer Vision and Pattern Recognition · Computer Science 2020-07-30 Shi Chen , Ming Jiang , Jinhui Yang , Qi Zhao

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…

Computation and Language · Computer Science 2025-11-04 Yuxuan Hu , Jianchao Tan , Jiaqi Zhang , Wen Zan , Pingwei Sun , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai , Jing Zhang

Neuroscientists classify neurons into different types that perform similar computations at different locations in the visual field. Traditional methods for neural system identification do not capitalize on this separation of 'what' and…

Machine Learning · Statistics 2018-01-30 David A. Klindt , Alexander S. Ecker , Thomas Euler , Matthias Bethge

Reason and inference require process as well as memory skills by humans. Neural networks are able to process tasks like image recognition (better than humans) but in memory aspects are still limited (by attention mechanism, size). Recurrent…

Machine Learning · Computer Science 2017-03-03 Amit Sahu

Attention Mechanism is a widely used method for improving the performance of convolutional neural networks (CNNs) on computer vision tasks. Despite its pervasiveness, we have a poor understanding of what its effectiveness stems from. It is…

Computer Vision and Pattern Recognition · Computer Science 2021-06-30 Xiang Ye , Zihang He , Heng Wang , Yong Li

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…