用自适应语义树重构表格，提升复杂表格问答的推理能力
ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering
- 将表格转为逻辑语义树，动态适配不同规模表结构
- 双模式推理：文本导航与符号代码验证结合，准确率领先
- 适合需要高精度表格理解的AI系统开发者
表格序列化仍是大语言模型在复杂表格问答中的关键瓶颈，受限于结构忽视、表示鸿沟和推理不透明等问题。现有序列化方法难以捕捉显式层级关系且缺乏模式灵活性，而当前基于树的方法又存在语义适应性不足。为此，我们提出ASTRA（自适应语义树推理架构），包含AdaSTR和DuTR两个核心模块。首先，引入AdaSTR，利用大模型的全局语义感知能力，将表格重构为逻辑语义树，显式建模层级依赖，并通过自适应机制根据表格规模优化构建策略。其次，在此结构基础上，提出DuTR双模式推理框架，融合基于树搜索的文本导航实现语言对齐，以及符号代码执行实现精确验证。在多个复杂表格基准测试中，该方法达到当前最优（SOTA）性能。
原文摘要 · Abstract (English)
Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering, hindered by challenges such as structural neglect, representation gaps, and reasoning opacity. Existing serialization methods fail to capture explicit hierarchies and lack schema flexibility, while current tree-based approaches suffer from limited semantic adaptability. To address these limitations, we propose ASTRA (Adaptive Semantic Tree Reasoning Architecture) including two main modules, AdaSTR and DuTR. First, we introduce AdaSTR, which leverages the global semantic awareness of LLMs to reconstruct tables into Logical Semantic Trees. This serialization explicitly models hierarchical dependencies and employs an adaptive mechanism to optimize construction strategies based on table scale. Second, building on this structure, we present DuTR, a dual-mode reasoning framework that integrates tree-search-based textual navigation for linguistic alignment and symbolic code execution for precise verification. Experiments on complex table benchmarks demonstrate that our method achieves state-of-the-art (SOTA) performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。