5 results for "Schelter, Sebastian"
Showing 1–5 · 0.20 seconds · RSS
-
Preprint Full text
SemPipes -- Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines
Real-world machine learning on tabular data relies on complex data preparation pipelines for prediction, data integration, augmentation, and debugging. Designing these pipelines requires substantial domain expertise and engineering effort, motivating the question of how large language models (LLMs)…
-
Preprint Full text
PrismaDV: Automated Task-Aware Data Unit Test Generation
Data is a central resource for modern enterprises, and data validation is essential for ensuring the reliability of downstream applications. However, existing automated data unit testing frameworks are largely task-agnostic: they validate datasets without considering the semantics and requirements…
-
Preprint Full text
ERASE -- A Real-World Aligned Benchmark for Unlearning in Recommender Systems
Machine unlearning (MU) enables the removal of selected training data from trained models, to address privacy compliance, security, and liability issues in recommender systems. Existing MU benchmarks poorly reflect real-world recommender settings: they focus primarily on collaborative filtering…
-
Preprint Full text
Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration
Retrieval-augmented generation (RAG) enhances LLM reasoning in knowledge-intensive tasks, but existing RAG pipelines incur substantial retrieval and generation overhead when applied to large-scale entity matching. To address this limitation, we introduce CE-RAG4EM, a cost-efficient RAG architecture…
-
Preprint Full text
SemBench: A Benchmark for Semantic Query Processing Engines
We present a benchmark targeting a novel class of systems: semantic query processing engines. Those systems rely inherently on generative and reasoning capabilities of state-of-the-art large language models (LLMs). They extend SQL with semantic operators, configured by natural language…