Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Impact, Detection, and Mitigation

arXiv:2609.36384 · cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes

Sources

• Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
• Griffin: Towards a Graph-Centric Relational Database Foundation Model
• KumoRFM-2: Scaling Foundation Models for Relational Learning
• Relational In-Context Learning via Synthetic Pre-training with Structural Prior
• OpenRFM: Dissecting Relational In-Context Learning
• ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
• GRAFT: Auditing Graph Neural Networks via Global Feature Attribution
• Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
• Task Scarcity and Label Leakage in Relational Transfer Learning
• TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
• The CTU Prague Relational Learning Repository
• TabPFN-3: Technical Report
• PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models
• RelBench v2: A Large-Scale Benchmark and Repository for Relational Data

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems