Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding

Table understanding is key to addressing challenging downstream tasks such as table-based question answering and fact verification.Recent works have focused on leveraging Chainof-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 longterm 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 stateof-the-art performance on WikiTableQuestions and TabFact datasets.