English
Related papers

Related papers: AttnLRP: Attention-Aware Layer-Wise Relevance Prop…

200 papers

Explainable AI (XAI) methods help identify which image regions influence a model's prediction, but often face a trade-off between detail and interpretability. Layer-wise Relevance Propagation (LRP) offers a model-aware alternative. However,…

Machine Learning · Computer Science 2025-10-02 Emerald Zhang , Julian Weaver , Samantha R Santacruz , Edward Castillo

Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their…

Computation and Language · Computer Science 2023-10-26 Mansi Sakarvadia , Arham Khan , Aswathy Ajith , Daniel Grzenda , Nathaniel Hudson , André Bauer , Kyle Chard , Ian Foster

Diffusion Large Language Models (DLLMs) have emerged as a powerful alternative to autoregressive models, enabling parallel token generation across multiple positions. However, preference alignment of DLLMs remains challenging due to high…

Computation and Language · Computer Science 2026-02-04 Liang Lin , Feng Xiong , Zengbin Wang , Kun Wang , Junhao Dong , Xuecai Hu , Yong Wang , Xiangxiang Chu

Layer-wise Relevance Propagation (LRP) provides principled attribution for neural networks through conservation properties and foundations in Deep Taylor Decomposition. However, existing implementations operate at the module level,…

Machine Learning · Computer Science 2026-03-24 Kevin Lee , Duncan Smith-Halverson , Pablo Millan Arias

Deep learning models are widely applied in the signal processing community, yet their inner working procedure is often treated as a black box. In this paper, we investigate the use of eXplainable Artificial Intelligence (XAI) techniques to…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-29 Luca Comanducci , Fabio Antonacci , Augusto Sarti

Recently, a technique called Layer-wise Relevance Propagation (LRP) was shown to deliver insightful explanations in the form of input space relevances for understanding feed-forward neural network classification decisions. In the present…

Computation and Language · Computer Science 2017-08-08 Leila Arras , Grégoire Montavon , Klaus-Robert Müller , Wojciech Samek

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Dimitrios Kafetzis , Ramin Khalili , Iordanis Koutsopoulos

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural language processing…

Computation and Language · Computer Science 2016-06-24 Leila Arras , Franziska Horn , Grégoire Montavon , Klaus-Robert Müller , Wojciech Samek

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Computation and Language · Computer Science 2024-12-06 Ximing Wen

We study how large language models recall relational knowledge during text generation, with a focus on identifying latent representations suitable for relation classification via linear probes. Prior work shows how attention heads and MLPs…

Computation and Language · Computer Science 2026-04-24 Nicholas Popovič , Michael Färber

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Machine Learning · Computer Science 2021-02-26 Yujing Wang , Yaming Yang , Jiangang Bai , Mingliang Zhang , Jing Bai , Jing Yu , Ce Zhang , Gao Huang , Yunhai Tong

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Computation and Language · Computer Science 2024-10-18 Ruiqing Yan , Linghan Zheng , Xingbo Du , Han Zou , Yufeng Guo , Jianfei Yang

Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension…

Machine Learning · Computer Science 2025-05-27 Toshiaki Koike-Akino , Xiangyu Chen , Jing Liu , Ye Wang , Pu , Wang , Matthew Brand

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…

Artificial Intelligence · Computer Science 2025-02-10 Junyang Zhang , Mu Yuan , Ruiguang Zhong , Puhan Luo , Huiyou Zhan , Ningkang Zhang , Chengchen Hu , Xiangyang Li

Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference. Prior work on linear or hybrid attention typically replaces…

The success of Transformer-based Language Models (LMs) stems from their attention mechanism. While this mechanism has been extensively studied in explainability research, particularly through the attention values obtained during the forward…

Computation and Language · Computer Science 2024-12-24 Shahar Katz , Lior Wolf

As Transformers have become state-of-the-art models for natural language processing (NLP) tasks, the need to understand and explain their predictions is increasingly apparent. Especially in unsupervised applications, such as information…

Computation and Language · Computer Science 2024-05-13 Alexandros Vasileiou , Oliver Eberle

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Computation and Language · Computer Science 2019-02-01 Thomas Zenkel , Joern Wuebker , John DeNero