# iGAiVA: Integrated Generative AI and Visual Analytics in a Machine Learning Workflow for Text Classification

arXiv: https://arxiv.org/abs/2409.15848 · HTML: https://mlsanity.com/paper/2409.15848/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 127 references that are in the map.
- First posted on arXiv 24 Sep 2024.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [A Survey on Data Augmentation for Text Classification](https://mlsanity.com/paper/2107.03158/) (2021)
- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://mlsanity.com/paper/2210.07321/) (2022)
- [explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning](https://mlsanity.com/paper/1908.00087/) (2019)
- [Visual Reinforcement Learning with Self-Supervised 3D Representations](https://mlsanity.com/paper/2210.07241/) (2022)
- [Short Text Topic Modeling Techniques, Applications, and Performance: A Survey](https://mlsanity.com/paper/1904.07695/) (2019)
- [Towards Better Analysis of Machine Learning Models: A Visual Analytics Perspective](https://mlsanity.com/paper/1702.01226/) (2017)
- [OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples](https://mlsanity.com/paper/2002.03103/) (2020)
- [M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis](https://mlsanity.com/paper/2107.08264/) (2021)
- [A Unified Understanding of Deep NLP Models for Text Classification](https://mlsanity.com/paper/2206.09355/) (2022)
- [Visual Comparison of Language Model Adaptation](https://mlsanity.com/paper/2208.08176/) (2022)
- [Semantic Concept Spaces: Guided Topic Model Refinement using Word-Embedding Projections](https://mlsanity.com/paper/1908.00475/) (2019)
- [VisRuler: Visual Analytics for Extracting Decision Rules from Bagged and Boosted Decision Trees](https://mlsanity.com/paper/2112.00334/) (2021)
- [VIANA: Visual Interactive Annotation of Argumentation](https://mlsanity.com/paper/1907.12413/) (2019)
- [Online Visual Analytics of Text Streams](https://mlsanity.com/paper/1512.04042/) (2015)
- [HypoML: Visual Analysis for Hypothesis-based Evaluation of Machine Learning Models](https://mlsanity.com/paper/2002.05271/) (2020)
- [Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization](https://mlsanity.com/paper/2010.12606/) (2020)
- [Visualizing Ensemble Predictions of Music Mood](https://mlsanity.com/paper/2112.07627/) (2021)
- [Real-Time Visual Analysis of High-Volume Social Media Posts](https://mlsanity.com/paper/2108.03052/) (2021)
- [ViS-'A-ViS : Detecting Similar Patterns in Annotated Literary Text](https://mlsanity.com/paper/2009.02063/) (2020)
- [CommAID: Visual Analytics for Communication Analysis through Interactive Dynamics Modeling](https://mlsanity.com/paper/2106.06334/) (2021)
- [Understanding the Effects of Visualizing Missing Values on Visual Data Exploration](https://mlsanity.com/paper/2109.08723/) (2021)

## Built on by (most cited first, 2 of 2)

- [A Review on Large Language Models for Visual Analytics](https://mlsanity.com/paper/2503.15176/) (2025)
- [AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification](https://mlsanity.com/paper/2508.10000/) (2025)

## Abstract (arXiv)

In developing machine learning (ML) models for text classification, one common challenge is that the collected data is often not ideally distributed, especially when new classes are introduced in response to changes of data and tasks. In this paper, we present a solution for using visual analytics (VA) to guide the generation of synthetic data using large language models. As VA enables model developers to identify data-related deficiency, data synthesis can be targeted to address such deficiency. We discuss different types of data deficiency, describe different VA techniques for supporting their identification, and demonstrate the effectiveness of targeted data synthesis in improving model accuracy. In addition, we present a software tool, iGAiVA, which maps four groups of ML tasks into four VA views, integrating generative AI and VA into an ML workflow for developing and improving text classification models.