Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.17005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918129655873536 |
|---|---|
| author | Nguyen, Thi-Nhung Ngo, Hoang Phung, Dinh Vu, Thuy-Trang Nguyen, Dat Quoc |
| author_facet | Nguyen, Thi-Nhung Ngo, Hoang Phung, Dinh Vu, Thuy-Trang Nguyen, Dat Quoc |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17005 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding Nguyen, Thi-Nhung Ngo, Hoang Phung, Dinh Vu, Thuy-Trang Nguyen, Dat Quoc Computation and Language 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. |
| title | Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.17005 |