English
Related papers

Related papers: Improving Neuron-level Interpretability with White…

200 papers

Transformer architectures have achieved great success in solving natural language tasks, which learn strong language representations from large-scale unlabeled texts. In this paper, we seek to go further beyond and explore a new logical…

Computation and Language · Computer Science 2023-02-21 Jianshu Chen

Many practical applications require training of semantic segmentation models on unlabelled datasets and their execution on low-resource hardware. Distillation from a trained source model may represent a solution for the first but does not…

Computer Vision and Pattern Recognition · Computer Science 2024-02-21 Claudia Cuttano , Antonio Tavera , Fabio Cermelli , Giuseppe Averta , Barbara Caputo

We present structured perceptron training for neural network transition-based dependency parsing. We learn the neural network representation using a gold corpus augmented by a large number of automatically parsed sentences. Given this fixed…

Computation and Language · Computer Science 2015-06-23 David Weiss , Chris Alberti , Michael Collins , Slav Petrov

Deep learning models have become popular in the analysis of tabular data, as they address the limitations of decision trees and enable valuable applications like semi-supervised learning, online learning, and transfer learning. However,…

Machine Learning · Computer Science 2024-02-29 Jiaqi Luo , Shixin Xu

Understanding the function of individual neurons within language models is essential for mechanistic interpretability research. We propose $\textbf{Neuron to Graph (N2G)}$, a tool which takes a neuron and its dataset examples, and…

Machine Learning · Computer Science 2023-04-26 Alex Foote , Neel Nanda , Esben Kran , Ionnis Konstas , Fazl Barez

Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by…

Computation and Language · Computer Science 2019-11-05 Yau-Shian Wang , Hung-Yi Lee , Yun-Nung Chen

Large language models have achieved remarkable success but remain largely black boxes with poorly understood internal mechanisms. To address this limitation, many researchers have proposed various interpretability methods including…

Machine Learning · Computer Science 2025-10-17 Zihao Fu , Ming Liao , Chris Russell , Zhenguang G. Cai

Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model. Existing methods primarily focus on accuracy and sparsity but the generated pathways may…

Computer Vision and Pattern Recognition · Computer Science 2023-09-19 Xinmiao Lin , Wentao Bao , Qi Yu , Yu Kong

Large language models (LLMs) have shown great promise in machine translation, but they still struggle with contextually dependent terms, such as new or domain-specific words. This leads to inconsistencies and errors that are difficult to…

Computation and Language · Computer Science 2024-10-29 Meiqi Chen , Fandong Meng , Yingxue Zhang , Yan Zhang , Jie Zhou

Nonlocal self-similarity within natural images has become an increasingly popular prior in deep-learning models. Despite their successful image restoration performance, such models remain largely uninterpretable due to their black-box…

Image and Video Processing · Electrical Eng. & Systems 2023-06-06 Nikola Janjušević , Amirhossein Khalilian-Gourtani , Adeen Flinker , Yao Wang

Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that…

Computation and Language · Computer Science 2016-11-22 Zhaopeng Tu , Yang Liu , Lifeng Shang , Xiaohua Liu , Hang Li

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

Neural networks are growing more capable on their own, but we do not understand their neural mechanisms. Understanding these mechanisms' decision-making processes, or mechanistic interpretability, enables (1) accountability and control in…

Computation and Language · Computer Science 2026-03-02 Mason Kadem , Rong Zheng

Recent deep learning methods for fMRI-based diagnosis have achieved promising accuracy by modeling functional connectivity networks. However, standard approaches often struggle with noisy interactions, and conventional post-hoc attribution…

Machine Learning · Computer Science 2026-02-25 Kunyu Zhang , Yanwu Yang , Jing Zhang , Xiangjie Shi , Shujian Yu

Progress in natural language processing (NLP) models that estimate representations of word sequences has recently been leveraged to improve the understanding of language processing in the brain. However, these models have not been…

Neurons and Cognition · Quantitative Biology 2019-11-11 Dan Schwartz , Mariya Toneva , Leila Wehbe

We present a systematic evaluation framework - thirty-seven analyses, 153 statistical tests, four cell types, two perturbation modalities - for assessing mechanistic interpretability in single-cell foundation models. Applying this framework…

Genomics · Quantitative Biology 2026-02-20 Ihor Kendiukhov

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Machine Learning · Computer Science 2025-11-26 Wei Chen , Jingxi Yu , Zichen Miao , Qiang Qiu

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization,…

Machine Learning · Computer Science 2021-03-01 Shohei Kubota , Hideaki Hayashi , Tomohiro Hayase , Seiichi Uchida

The interpretability of deep learning models has raised extended attention these years. It will be beneficial if we can learn an interpretable structure from deep learning models. In this paper, we focus on Recurrent Neural Networks~(RNNs)…

Neural and Evolutionary Computing · Computer Science 2020-01-15 Bo-Jian Hou , Zhi-Hua Zhou

Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Hu Gao , Xiaoning Lei , Xichen Xu , Depeng Dang , Lizhuang Ma
‹ Prev 1 8 9 10 Next ›