AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers

• URL: http://arxiv.org/abs/2402.05602v2
• Date: Mon, 10 Jun 2024 09:58:55 GMT
• Title: AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
• Authors: Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Aakriti Jain, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek,
• Abstract summary: Large Language Models are prone to biased predictions and hallucinations. achieving faithful attributions for the entirety of a black-box transformer model and maintaining computational efficiency is an unsolved challenge.
• Score: 14.147646140595649
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models are prone to biased predictions and hallucinations, underlining the paramount importance of understanding their model-internal reasoning process. However, achieving faithful attributions for the entirety of a black-box transformer model and maintaining computational efficiency is an unsolved challenge. By extending the Layer-wise Relevance Propagation attribution method to handle attention layers, we address these challenges effectively. While partial solutions exist, our method is the first to faithfully and holistically attribute not only input but also latent representations of transformer models with the computational efficiency similar to a single backward pass. Through extensive evaluations against existing methods on LLaMa 2, Mixtral 8x7b, Flan-T5 and vision transformer architectures, we demonstrate that our proposed approach surpasses alternative methods in terms of faithfulness and enables the understanding of latent representations, opening up the door for concept-based explanations. We provide an LRP library at https://github.com/rachtibat/LRP-eXplains-Transformers.

Related papers

• DAPE V2: Process Attention Score as Feature Map for Length Extrapolation [63.87956583202729]
  We conceptualize attention as a feature map and apply the convolution operator to mimic the processing methods in computer vision. The novel insight, which can be adapted to various attention-related models, reveals that the current Transformer architecture has the potential for further evolution.
  arXiv  Detail & Related papers  (2024-10-07T07:21:49Z)
• The Mechanics of Conceptual Interpretation in GPT Models: Interpretative Insights [10.777646083061395]
  We introduce concept editing'', an innovative variation of knowledge editing that uncovers conceptualisation mechanisms within large language models. We analyse the Multi-Layer Perceptron (MLP), Multi-Head Attention (MHA), and hidden state components of transformer models. Our work highlights the complex, layered nature of semantic processing in LLMs and the challenges of isolating and modifying specific concepts within these models.
  arXiv  Detail & Related papers  (2024-08-05T18:50:08Z)
• Skip-Layer Attention: Bridging Abstract and Detailed Dependencies in Transformers [56.264673865476986]
  This paper introduces Skip-Layer Attention (SLA) to enhance Transformer models. SLA improves the model's ability to capture dependencies between high-level abstract features and low-level details. Our implementation extends the Transformer's functionality by enabling queries in a given layer to interact with keys and values from both the current layer and one preceding layer.
  arXiv  Detail & Related papers  (2024-06-17T07:24:38Z)
• Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers [12.986126243018452]
  We introduce the Softmax-Linked Additive Log-Odds Model (SLALOM), a novel surrogate model specifically designed to align with the transformer framework. SLALOM demonstrates the capacity to deliver a range of faithful and insightful explanations across both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-05-22T11:14:00Z)
• Pyramid Hierarchical Transformer for Hyperspectral Image Classification [1.9427851979929982]
  We propose a pyramid-based hierarchical transformer (PyFormer) This innovative approach organizes input data hierarchically into segments, each representing distinct abstraction levels. Results underscore the superiority of the proposed method over traditional approaches.
  arXiv  Detail & Related papers  (2024-04-23T11:41:19Z)
• Approximated Prompt Tuning for Vision-Language Pre-trained Models [54.326232586461614]
  In vision-language pre-trained models, prompt tuning often requires a large number of learnable tokens to bridge the gap between the pre-training and downstream tasks. We propose a novel Approximated Prompt Tuning (APT) approach towards efficient VL transfer learning.
  arXiv  Detail & Related papers  (2023-06-27T05:43:47Z)
• XAI for Transformers: Better Explanations through Conservative Propagation [60.67748036747221]
  We show that the gradient in a Transformer reflects the function only locally, and thus fails to reliably identify the contribution of input features to the prediction. Our proposal can be seen as a proper extension of the well-established LRP method to Transformers.
  arXiv  Detail & Related papers  (2022-02-15T10:47:11Z)
• A Practical Survey on Faster and Lighter Transformers [0.9176056742068811]
  The Transformer is a model solely based on the attention mechanism that is able to relate any two positions of the input sequence. It has improved the state-of-the-art across numerous sequence modelling tasks. However, its effectiveness comes at the expense of a quadratic computational and memory complexity with respect to the sequence length.
  arXiv  Detail & Related papers  (2021-03-26T17:54:47Z)
• Transformers Solve the Limited Receptive Field for Monocular Depth Prediction [82.90445525977904]
  We propose TransDepth, an architecture which benefits from both convolutional neural networks and transformers. This is the first paper which applies transformers into pixel-wise prediction problems involving continuous labels.
  arXiv  Detail & Related papers  (2021-03-22T18:00:13Z)
• Bayesian Transformer Language Models for Speech Recognition [59.235405107295655]
  State-of-the-art neural language models (LMs) represented by Transformers are highly complex. This paper proposes a full Bayesian learning framework for Transformer LM estimation.
  arXiv  Detail & Related papers  (2021-02-09T10:55:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.