{"ID":2879128,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17005","arxiv_id":"2508.17005","title":"Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding","abstract":"Table understanding is key to addressing challenging downstream tasks such as table-based question answering and fact verification. Recent works have focused on leveraging Chain-of-Thought and question decomposition to solve complex questions requiring multiple operations on tables. However, these methods often suffer from a lack of explicit long-term planning and weak inter-step connections, leading to miss constraints within questions. In this paper, we propose leveraging the long-term planning capabilities of large language models (LLMs) to enhance table understanding. Our approach enables the execution of a long-term plan, where the steps are tightly interconnected and serve the ultimate goal, an aspect that methods based on Chain-of-Thought and question decomposition lack. In addition, our method effectively minimizes the inclusion of unnecessary details in the process of solving the next short-term goals, a limitation of methods based on Chain-of-Thought. Extensive experiments demonstrate that our method outperforms strong baselines and achieves state-of-the-art performance on WikiTableQuestions and TabFact datasets.","short_abstract":"Table understanding is key to addressing challenging downstream tasks such as table-based question answering and fact verification. Recent works have focused on leveraging Chain-of-Thought and question decomposition to solve complex questions requiring multiple operations on tables. However, these methods often suffer...","url_abs":"https://arxiv.org/abs/2508.17005","url_pdf":"https://arxiv.org/pdf/2508.17005v1","authors":"[\"Thi-Nhung Nguyen\",\"Hoang Ngo\",\"Dinh Phung\",\"Thuy-Trang Vu\",\"Dat Quoc Nguyen\"]","published":"2025-08-23T12:24:35Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}