Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillation

• URL: http://arxiv.org/abs/2603.11342v1
• Date: Wed, 11 Mar 2026 22:16:11 GMT
• Title: Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillation
• Abstract summary: This paper introduces a new approach for evaluating explainability methods in seq2seq models.<n>We use teacher-derived attribution maps as a structured side signal to guide a student model.<n>We also introduce an Attributor transformer that learns to reconstruct the teacher's attribution map.
• Score: 1.373282478189168
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The study of the attribution of input features to the output of neural network models is an active area of research. While numerous Explainable AI (XAI) techniques have been proposed to interpret these models, the systematic and automated evaluation of these methods in sequence-to-sequence (seq2seq) models is less explored. This paper introduces a new approach for evaluating explainability methods in transformer-based seq2seq models. We use teacher-derived attribution maps as a structured side signal to guide a student model, and quantify the utility of different attribution methods through the student's ability to simulate targets. Using the Inseq library, we extract attribution scores over source-target sequence pairs and inject these scores into the attention mechanism of a student transformer model under four composition operators (addition, multiplication, averaging, and replacement). Across three language pairs (de-en, fr-en, ar-en) and attributions from Marian-MT and mBART models, Attention, Value Zeroing, and Layer Gradient $\times$ Activation consistently yield the largest gains in BLEU (and corresponding improvements in chrF) relative to baselines. In contrast, other gradient-based methods (Saliency, Integrated Gradients, DeepLIFT, Input $\times$ Gradient, GradientShap) lead to smaller and less consistent improvements. These results suggest that different attribution methods capture distinct signals and that attention-derived attributions better capture alignment between source and target representations in seq2seq models. Finally, we introduce an Attributor transformer that, given a source-target pair, learns to reconstruct the teacher's attribution map. Our findings demonstrate that the more accurately the Attributor can reproduce attribution maps, the more useful an injection of those maps is for the downstream task. The source code can be found on GitHub.

Related papers

• Foundation Models in Dermatopathology: Skin Tissue Classification [0.05397680436511065]
  This study evaluates the performance of two foundation models, UNI and Virchow2, as feature extractors for classifying whole-slide images.<n> Patch-level embeddings were aggregated into slide-level features using a mean-aggregation strategy.<n>Results demonstrate that patch-level features extracted using Virchow2 outperformed those extracted via UNI across most slide-level classifiers.
  arXiv  Detail & Related papers  (2025-10-24T17:21:43Z)
• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• Supervised Score-Based Modeling by Gradient Boosting [49.556736252628745]
  We propose a Supervised Score-based Model (SSM) which can be viewed as a gradient boosting algorithm combining score matching.<n>We provide a theoretical analysis of learning and sampling for SSM to balance inference time and prediction accuracy.<n>Our model outperforms existing models in both accuracy and inference time.
  arXiv  Detail & Related papers  (2024-11-02T07:06:53Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• Explainable Learning with Gaussian Processes [23.796560256071473]
  We take a principled approach to defining attributions under model uncertainty, extending the existing literature. We show that although GPR is a highly flexible and non-parametric approach, we can derive interpretable, closed-form expressions for the feature attributions. We also show that, when applicable, the exact expressions for GPR attributions are both more accurate and less computationally expensive than the approximations currently used in practice.
  arXiv  Detail & Related papers  (2024-03-11T18:03:02Z)
• Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals [14.741951369068877]
  We find that ubiquitous time series (TS) forecasting models are prone to severe overfitting. We introduce a dual-stream and subtraction mechanism, which is a deep Boosting ensemble learning method. The proposed method outperform existing state-of-the-art methods, yielding an average performance improvement of 11.9% across various datasets.
  arXiv  Detail & Related papers  (2024-02-04T03:54:31Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Generalizing Backpropagation for Gradient-Based Interpretability [103.2998254573497]
  We show that the gradient of a model is a special case of a more general formulation using semirings. This observation allows us to generalize the backpropagation algorithm to efficiently compute other interpretable statistics.
  arXiv  Detail & Related papers  (2023-07-06T15:19:53Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)
• Eigen-CAM: Class Activation Map using Principal Components [1.2691047660244335]
  This paper builds on previous ideas to cope with the increasing demand for interpretable, robust, and transparent models. The proposed Eigen-CAM computes and visualizes the principle components of the learned features/representations from the convolutional layers.
  arXiv  Detail & Related papers  (2020-08-01T17:14:13Z)
• Depthwise Discrete Representation Learning [2.728575246952532]
  Recent advancements in learning Discrete Representations have led to state of art results in tasks that involve Language, Audio and Vision. Some latent factors such as words, phonemes and shapes are better represented by discrete latent variables as opposed to continuous. Vector Quantized Variational Autoencoders (VQVAE) have produced remarkable results in multiple domains.
  arXiv  Detail & Related papers  (2020-04-11T18:57:13Z)

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.