Problem
Research questions and friction points this paper is trying to address.
table understanding
structural relationships
hierarchical table headers
DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table Understanding
🤖 AI Summary
本文提出DeepTable，通过结构注意力偏置和树路径编码方法增强大型语言模型对表格层级结构的理解能力，从而提高表格问答任务的性能。
📝 Abstract
Large language models (LLMs) have demonstrated strong performance in table understanding. However, they typically process table content and headers as linearized token sequences. This representation weakens the two-dimensional and hierarchical structural relationships encoded by multi-level row and column headers. Existing parameter-efficient fine-tuning methods incorporate basic row and column information but do not explicitly capture the rich structural dependencies induced by hierarchical table headers. We propose DeepTable, a structure-aware approach for table understanding with LLMs. DeepTable comprises two complementary components. Structural Attention Bias (SAB) introduces learnable biases into the attention logits to explicitly represent whether pairs of table tokens share the same row or column. Tree Path Encoding (TPE) represents each table token using the ancestor paths of its row and column headers, preserving its position within the multi-level table structure. We integrate DeepTable with TableLoRA (He et al., 2025) to inject structural information into parameter-efficient adaptation. Across three LLM backbones, DeepTable consistently improves the corresponding TableLoRA baselines on three table question answering benchmarks, achieving average gains of 7.42 points on HiTab, 3.23 points on WikiTQ, and 2.01 BLEU points on FeTaQA. These results demonstrate the effectiveness of the proposed structural biases across different LLM backbones.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Structural Attention Bias
Tree Path Encoding
Hierarchical Table Understanding
🔎 Similar Papers
No similar papers found.
