The paper "Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval" addresses the critical issue of table retrieval in open-domain question-answering systems. Traditional methods often assume that answers can be found in a single table or multiple tables identified through question decomposition, but this approach is insufficient for complex queries that require joining multiple tables. The authors propose a novel re-ranking method formulated as a mixed-integer program that considers both table-query relevance and table-table relevance, including the inference of join relationships. This method outperforms state-of-the-art approaches by up to 9.3% in F1 score for table retrieval and 5.4% in accuracy for end-to-end QA. The paper also discusses the challenges of real-world table retrieval, such as the need to retrieve multiple tables and the complexity of inferring join relationships, and provides a detailed evaluation on the Spider and Bird datasets, demonstrating the effectiveness of the proposed method.The paper "Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval" addresses the critical issue of table retrieval in open-domain question-answering systems. Traditional methods often assume that answers can be found in a single table or multiple tables identified through question decomposition, but this approach is insufficient for complex queries that require joining multiple tables. The authors propose a novel re-ranking method formulated as a mixed-integer program that considers both table-query relevance and table-table relevance, including the inference of join relationships. This method outperforms state-of-the-art approaches by up to 9.3% in F1 score for table retrieval and 5.4% in accuracy for end-to-end QA. The paper also discusses the challenges of real-world table retrieval, such as the need to retrieve multiple tables and the complexity of inferring join relationships, and provides a detailed evaluation on the Spider and Bird datasets, demonstrating the effectiveness of the proposed method.