← Back to all news
arXiv AI By Roshan Reddy Upendra, Alexandre Dorais, Joe Meyer, Andrew Pouret, Anastasios Lambrianos Stappas, Dinesh Katupputhur Ramprasath, Tom Palczewski, Minghua Li

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

Read the original on arXiv AI →

The paper investigates a new failure mode in relational in-context learning called support‑set target leakage, where target‑derived features appear only in the labeled support set and not in the query. The authors create 14 synthetic leaker types across 20 columns, evaluate a frozen relational encoder on RelBench databases, and use Integrated Gradients to identify and mitigate the most harmful leakers. Results show that target‑table leakers degrade performance most, while one‑ and two‑hop leakers are less consistently exploited, and that IG can partially recover performance by removing high‑ranked leakers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
4d ago

Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Model Dependence and Evaluation Reliability

arXiv:2609.36417v1 Announce Type: new Abstract: Relational in-context learning (ICL) uses labeled support examples and their linked relational context to predict labels for new queries. This creates...

By Roshan Reddy Upendra, Alexandre Dorais, Joe Meyer, Andrew Pouret, Anastasios Lambrianos Stappas, Dinesh Katupputhur Ramprasath, Viswanath Ganapathy, Tom Palczewski, Minghua Li
llms
More like this →
arXiv AI
Jun 4

OpenRFM: Dissecting Relational In-Context Learning

arXiv:2606. 04320v1 Announce Type: cross Abstract: Relational Foundation Models (RFMs) promise a single pre-trained predictor that, given any relational database, returns predictions in one forward pass via relational in-context learning (ICL).

By Zhikai Chen, Junyu Yin, Jialiang Gu, Siheng Xiong, Xiaoze Liu, Ruowang Zhang, Keren Zhou, Kai Guo
llms
More like this →
arXiv Machine Learning
1d ago

STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling

STEER is a sampling method for relational foundation models that reduces inference cost by focusing on the most relevant tables for a prediction task. It uses a large language model to rank foreign‑key edges in the database schema into relevance tiers, then assigns traversal probabilities based on these tiers. Evaluated on three state‑of‑the‑art RFMs, STEER cuts inference context size by roughly 40% on average while preserving or improving accuracy.

By Abdalla Mohamed, Ashraf Aboulnaga
llmsbenchmarks
More like this →
Hugging Face Trending Papers
Jun 29

FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks

We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a suite of task-specific decoders. Unlike existing tabular in-context learners, which entangle feature representations with a specific prediction target, our design produces \textit{target-agnostic} row embeddings that can be leveraged across a wide range of downstream tasks within a table-native in-context learning setup.

llmsragbenchmarks
More like this →