TAGAL: Tabular Data Generation using Agentic LLM Methods
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915478951165952 |
|---|---|
| author | Ronval, Benoît Dupont, Pierre Nijssen, Siegfried |
| author_facet | Ronval, Benoît Dupont, Pierre Nijssen, Siegfried |
| contents | The generation of data is a common approach to improve the performance of machine learning tasks, among which is the training of models for classification. In this paper, we present TAGAL, a collection of methods able to generate synthetic tabular data using an agentic workflow. The methods leverage Large Language Models (LLMs) for an automatic and iterative process that uses feedback to improve the generated data without any further LLM training. The use of LLMs also allows for the addition of external knowledge in the generation process. We evaluate TAGAL across diverse datasets and different aspects of quality for the generated data. We look at the utility of downstream ML models, both by training classifiers on synthetic data only and by combining real and synthetic data. Moreover, we compare the similarities between the real and the generated data. We show that TAGAL is able to perform on par with state-of-the-art approaches that require LLM training and generally outperforms other training-free approaches. These findings highlight the potential of agentic workflow and open new directions for LLM-based data generation methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04152 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TAGAL: Tabular Data Generation using Agentic LLM Methods Ronval, Benoît Dupont, Pierre Nijssen, Siegfried Machine Learning Artificial Intelligence The generation of data is a common approach to improve the performance of machine learning tasks, among which is the training of models for classification. In this paper, we present TAGAL, a collection of methods able to generate synthetic tabular data using an agentic workflow. The methods leverage Large Language Models (LLMs) for an automatic and iterative process that uses feedback to improve the generated data without any further LLM training. The use of LLMs also allows for the addition of external knowledge in the generation process. We evaluate TAGAL across diverse datasets and different aspects of quality for the generated data. We look at the utility of downstream ML models, both by training classifiers on synthetic data only and by combining real and synthetic data. Moreover, we compare the similarities between the real and the generated data. We show that TAGAL is able to perform on par with state-of-the-art approaches that require LLM training and generally outperforms other training-free approaches. These findings highlight the potential of agentic workflow and open new directions for LLM-based data generation methods. |
| title | TAGAL: Tabular Data Generation using Agentic LLM Methods |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.04152 |