2 papers
cs.AI2026
Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Model Dependence and Evaluation Reliability
Roshan Reddy Upendra, Alexandre Dorais, Joe Meyer +6
Relational in-context learning (ICL) uses labeled support examples and their linked relational context to predict labels for new queries. This creates a failure mode when target-de…
cs.AI2026
Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Impact, Detection, and Mitigation
Roshan Reddy Upendra, Alexandre Dorais, Joe Meyer +5
Relational in-context learning (ICL) conditions predictions on the labeled support examples and their linked tables, creating a failure mode when the support set contains target-de…