CRAFT: Training-Free Cascaded Retrieval for Tabular QA
This work addresses efficiency and adaptability issues in table question answering for domains with evolving data, though it is incremental as it builds on existing retrieval techniques.
The paper tackles the problem of high computational costs and limited adaptability in table question answering by proposing CRAFT, a cascaded retrieval approach that combines sparse and dense models, achieving better retrieval performance than state-of-the-art methods on NQ-Tables.
Table Question Answering (TQA) involves retrieving relevant tables from a large corpus to answer natural language queries. Traditional dense retrieval models, such as DTR and ColBERT, not only incur high computational costs for large-scale retrieval tasks but also require retraining or fine-tuning on new datasets, limiting their adaptability to evolving domains and knowledge. In this work, we propose $\textbf{CRAFT}$, a cascaded retrieval approach that first uses a sparse retrieval model to filter a subset of candidate tables before applying more computationally expensive dense models and neural re-rankers. Our approach achieves better retrieval performance than state-of-the-art (SOTA) sparse, dense, and hybrid retrievers. We further enhance table representations by generating table descriptions and titles using Gemini Flash 1.5. End-to-end TQA results using various Large Language Models (LLMs) on NQ-Tables, a subset of the Natural Questions Dataset, demonstrate $\textbf{CRAFT}$ effectiveness.