Open-Domain 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 DPR incur high computational costs for large-scale retrieval tasks and require retraining or fine-tuning on new datasets, limiting their adaptability to evolving domains and knowledge. We propose CRAFT, a zero-shot cascaded retrieval approach that first uses a sparse retrieval model to filter a subset of candidate tables before applying more computationally expensive dense models as re-rankers. To improve retrieval quality, we enrich table representations with descriptive titles and summaries generated by Gemini Flash 1.5, enabling richer semantic matching between queries and tabular structures. Our method outperforms state-of-the-art sparse, dense, and hybrid retrievers on the NQ-Tables dataset. It also demonstrates strong zero-shot performance on the more challenging OTT-QA benchmark, achieving competitive results at higher recall thresholds, where the task requires multi-hop reasoning across both textual passages and relational tables. This work establishes a scalable and adaptable paradigm for table retrieval, bridging the gap between fine-tuned architectures and lightweight, plug-and-play retrieval systems. Code and data are available at https://coral-lab-asu.github.io/CRAFT/

翻译：摘要：开放域表格问答（TQA）涉及从大规模语料库中检索相关表格以回答自然语言查询。传统稠密检索模型（如DTR和DPR）在大规模检索任务中计算成本高昂，且需要在新数据集上重新训练或微调，限制了其对动态演变领域和知识的适应性。我们提出CRAFT，一种零样本级联检索方法，首先使用稀疏检索模型过滤候选表格子集，再应用计算成本更高的稠密模型作为重排序器。为提升检索质量，我们利用Gemini Flash 1.5生成的描述性标题与摘要对表格表示进行增强，从而在查询与表格结构之间实现更丰富的语义匹配。该方法在NQ-Tables数据集上优于现有最优的稀疏、稠密及混合检索器，并在更具挑战性的OTT-QA基准测试中展现出强大的零样本性能——在需要跨文本段落与关系表格进行多跳推理的高召回率阈值下取得了具有竞争力的结果。本工作建立了可扩展且自适应的表格检索范式，弥合了微调架构与轻量级即插即用检索系统之间的差距。代码与数据详见https://coral-lab-asu.github.io/CRAFT/