The article details presented on this page reflect the published version of record. Readers may access the full-text PDF, review the citation information, and export the reference in supported citation formats.
Abstract
This paper introduces an interactive visual analytics framework designed to support exploratory analysis of neural network models for natural language inference through a perturbation-driven paradigm. Rather than treating trained models as static black boxes, the system enables users to dynamically manipulate inputs, internal attention mechanisms, and output predictions while observing corresponding changes across the processing pipeline. The interface integrates multiple coordinated views including bipartite graph and matrix representations of attention, barycentric coordinate plots for probabilistic predictions, and a pipeline visualization for tracking parameter updates to support hypothesis formation and causal reasoning about model behavior. A constrained optimization procedure, inspired by the margin-infused relaxed algorithm, allows users to correct erroneous predictions while minimizing parameter deviation and to compare the relative influence of encoder, attention, and classifier stages on prediction outcomes. The system also overlays syntactic dependency structures onto attention visualizations, enabling grammar-guided simplification and facilitating investigation of the relationship between linguistic structure and learned alignments. Evaluation with NLP researchers demonstrates that the tool supports a range of analytical tasks, including stability assessment, error diagnosis, attention editing, and comparative analysis of model components. The framework is implemented as a lightweight Python library that integrates with existing PyTorch models, lowering the barrier to adoption for routine model interrogation.
Keywords:Attention VisualizationNeural Language ModelsInterpretabilityVisual AnalyticsConstrained OptimizationPerturbationNatural Language Inference
Cite this Article
Use the following citation when referencing this publication in academic or professional work.
E. Pasula, "Perturbation-Driven Visual Analytics for Probing InternalRepresentations in Neural Language Models", Int. J. Intell. Syst. Data Sci., vol. 1, no. 3, Oct. 2026, doi: https://doi.org/10.67231/jpr65e97.
DOWNLOAD CITATION
Perturbation-Driven Visual Analytics for Probing InternalRepresentations in Neural Language Models | International Journal of Intelligent Systems and Data Science