Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.31550 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913174354132992 |
|---|---|
| author | Zhao, Yibin Shang, Fangxin Yang, Dingrui Wang, Yuqi |
| author_facet | Zhao, Yibin Shang, Fangxin Yang, Dingrui Wang, Yuqi |
| contents | Table question answering requires models to recover semantic relations encoded implicitly by two-dimensional layout, merged cells, and hierarchical headers. Current pipelines typically use HTML or Markdown as intermediate table representations, but these layout-oriented serializations introduce markup overhead and require large language models to infer header-cell alignments from row and column spans. We propose Semantic Triplet Restoration (STR), a protocol that rewrites each cell as an atomic fact <item path, feature path, value>, where the item path specifies the row-wise entity, the feature path specifies the hierarchical attribute, and the value contains the cell content. We also present TripletQL, a lightweight query-aware router that uses STR to select an appropriate rendering or filtered subset of triplets for each question. Across four Chinese and English table-QA benchmarks, STR matches or improves upon HTML-based baselines while reducing input tokens. The relative benefit grows for smaller language models and longer table contexts, suggesting that explicit semantic representations are especially useful under constrained inference budgets. Code and data are available at https://github.com/Phoenix-ni/STR.git . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_31550 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models Zhao, Yibin Shang, Fangxin Yang, Dingrui Wang, Yuqi Computation and Language Table question answering requires models to recover semantic relations encoded implicitly by two-dimensional layout, merged cells, and hierarchical headers. Current pipelines typically use HTML or Markdown as intermediate table representations, but these layout-oriented serializations introduce markup overhead and require large language models to infer header-cell alignments from row and column spans. We propose Semantic Triplet Restoration (STR), a protocol that rewrites each cell as an atomic fact <item path, feature path, value>, where the item path specifies the row-wise entity, the feature path specifies the hierarchical attribute, and the value contains the cell content. We also present TripletQL, a lightweight query-aware router that uses STR to select an appropriate rendering or filtered subset of triplets for each question. Across four Chinese and English table-QA benchmarks, STR matches or improves upon HTML-based baselines while reducing input tokens. The relative benefit grows for smaller language models and longer table contexts, suggesting that explicit semantic representations are especially useful under constrained inference budgets. Code and data are available at https://github.com/Phoenix-ni/STR.git . |
| title | Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.31550 |