כאשר תנאי רטיין נכנסים לסכסוך: הפחתת התנגשות זיכרון-רטיין בנתוני טבלה

תקציר מקורי באנגליתarXiv:2609.06786v1 Announce Type: new Abstract: 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 attribute ranges, and common output spaces. Consequently, a forget row may have nearby retain rows that rely on the same high-signal attributes, causing reta