ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering

2026-04-10

AI Summary

This work addresses the limitations of large language models in complex table-based question answering, which stem from structural information loss during table serialization, semantic representation gaps, and opaque reasoning processes. To overcome these challenges, the authors propose ASTRA, a novel architecture featuring an Adaptive Semantic Table Reconstruction (AdaSTR) module that converts tables into logical semantic trees to explicitly model hierarchical dependencies. Additionally, ASTRA incorporates a Dual-Mode Tree-based Reasoning (DuTR) framework that synergistically combines tree-search-driven textual navigation with symbolic code execution, enabling precise and interpretable inference. By balancing semantic flexibility with reasoning fidelity, the proposed method achieves state-of-the-art performance across multiple challenging table QA benchmarks.

Technology Category

• Natural Language Processing: Question Answering
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• table question answering
• table serialization
• semantic tree
• hierarchical structure
• reasoning opacity

Innovation

• Adaptive Semantic Tree
• Table Question Answering
• Logical Semantic Tree
• Dual-mode Reasoning
• Tree-based Serialization