Something's Fishy In The Data Lake: A Critical Re-evaluation of Table Union Search Benchmarks
This work addresses the problem of unreliable evaluation in table union search for researchers and practitioners, highlighting incremental improvements in benchmarking.
The paper identifies limitations in existing table union search benchmarks that allow simple baselines to outperform sophisticated methods, suggesting current evaluations fail to isolate semantic understanding gains. It proposes criteria for future benchmarks to improve reliability.
Recent table representation learning and data discovery methods tackle table union search (TUS) within data lakes, which involves identifying tables that can be unioned with a given query table to enrich its content. These methods are commonly evaluated using benchmarks that aim to assess semantic understanding in real-world TUS tasks. However, our analysis of prominent TUS benchmarks reveals several limitations that allow simple baselines to perform surprisingly well, often outperforming more sophisticated approaches. This suggests that current benchmark scores are heavily influenced by dataset-specific characteristics and fail to effectively isolate the gains from semantic understanding. To address this, we propose essential criteria for future benchmarks to enable a more realistic and reliable evaluation of progress in semantic table union search.