Quality-controlled synthetic oversampling for imbalanced tabular classification using large language models

Many tabular classification tasks involve imbalanced classes, but synthetic oversampling can produce rows that violate feature constraints or duplicate existing observations. We present QualSynth, a training-free framework that prompts a large language model to make sparse edits to real minority-class rows under data-derived feature constraints and a machine-readable output contract. A deterministic validation layer checks each candidate’s structure, values, and duplication before admitting it to the training set. We evaluated QualSynth on eight benchmark datasets with ten seeds against four synthetic oversamplers, including the widely used SMOTE, and class-weighted learning without augmentation. QualSynth achieved the highest F1 score among the synthetic oversamplers on four datasets, while SMOTE had the best average ranks. In equivalence tests, QualSynth and SMOTE differed by less than prespecified margins of 0.03 in F1 score and 0.02 in the area under the receiver operating characteristic curve (ROC-AUC). After correction for multiple comparisons, the only pairwise difference was higher ROC-AUC for QualSynth than for the diffusion model TabDDPM. Class weighting alone had the best overall ranks, and no augmentation strategy improved aggregate ROC-AUC over the unweighted reference. QualSynth is therefore a controlled, inspectable option for minority-class augmentation, with predictive utility comparable to SMOTE’s.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-18
DOI
https://doi.org/10.1038/s41598-026-80920-4
Primary Topic
Imbalanced Data Classification Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Quality-controlled synthetic oversampling for imbalanced tabular classification using large language models

Muhammed Abdulhamid Karabıyık, Tunç Aşuroğlu, Bahaeddin Türkoğlu, Asim Sinan Yuksel
2 links
Scientific Reports
Imbalanced Data Classification Techniques
article

Quality-controlled synthetic oversampling for imbalanced tabular classification using large language models

Muhammed Abdulhamid Karabıyık, Tunç Aşuroğlu, Bahaeddin Türkoğlu, Asim Sinan Yuksel
article en

Abstract

Many tabular classification tasks involve imbalanced classes, but synthetic oversampling can produce rows that violate feature constraints or duplicate existing observations. We present QualSynth, a training-free framework that prompts a large language model to make sparse edits to real minority-class rows under data-derived feature constraints and a machine-readable output contract. A deterministic validation layer checks each candidate’s structure, values, and duplication before admitting it to the training set. We evaluated QualSynth on eight benchmark datasets with ten seeds against four synthetic oversamplers, including the widely used SMOTE, and class-weighted learning without augmentation. QualSynth achieved the highest F1 score among the synthetic oversamplers on four datasets, while SMOTE had the best average ranks. In equivalence tests, QualSynth and SMOTE differed by less than prespecified margins of 0.03 in F1 score and 0.02 in the area under the receiver operating characteristic curve (ROC-AUC). After correction for multiple comparisons, the only pairwise difference was higher ROC-AUC for QualSynth than for the diffusion model TabDDPM. Class weighting alone had the best overall ranks, and no augmentation strategy improved aggregate ROC-AUC over the unweighted reference. QualSynth is therefore a controlled, inspectable option for minority-class augmentation, with predictive utility comparable to SMOTE’s.

Scientific Reports
Ankara University (TR), Tampere University (FI), Süleyman Demirel Üniversitesi (TR), Konya Technical University (TR), University of Tampere (FI), VTT Technical Research Centre of Finland (FI)
Imbalanced Data Classification Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon