SOURCE-LINKED INTELLIGENCE

When Retain Constraints Conflict: Mitigating Forget-Retain Interference in Tabular Data

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Machine unlearning aims to remove the influence of designated training data while preserving model utility, but its behavior on tabular data remains underexplored. This gap is important because tabular prediction is widely used in high-stakes domains and is increasingly adapted to language models through record serialization and schema-aware prompting. We identify a key challenge that distinguishes tabular unlearning from unlearning in free-form text or other modalities: schema-induced forget-retain overlap. In serialized tabular data, records share fixed column-name/value slots, similar attri

Read original source ↗ Open in workspace

recordType

paper

region

Global