arXiv cs.CL· Eunbin Kim, Hyeonseok Kang, Sangkeun Jung·· 13 小时前AI 评分31
LTEM：面向表格理解与生成的 LLM 友好型表格增强 Markdown
LTEM: LLM-Friendly Table-Enhanced Markdown for Table Understanding and Generation
AI 导读
研究者提出 LTEM，一种形式化定义、对 Markdown 做最小扩展的表格格式，可显式编码合并单元格与多级表头。在五个 SOTA LLM 上的实验显示，LTEM 表格理解准确率与 HTML 相当，准确率-token 权衡优于 HTML 和 LaTeX，无效回答显著少于 LaTeX；表格生成表现与 MultiMarkdown 相当，HTML 最佳。
正文 · 原文
Abstract:Tables in real-world documents, including scientific papers, financial reports, and statistical summaries, frequently use merged cells, multi-level headers, and sectioned layouts. Yet the lightweight formats LLMs handle best (Markdown, CSV) cannot express these structures, while expressive formats (HTML, LaTeX) impose excessive token cost and parsing complexity. To enable systematic analysis of this trade-off, we introduce a taxonomy decomposing table structure into six atomic features (F1-F6) and corresponding complexity levels (L1-L6), and construct STB (Synthetic Table Benchmark), a controlled benchmark with 1,089 tables systematically distributed across complexity levels. Using this framework, we propose LTEM (LLM-friendly Table-Enhanced Markdown), a formally specified, minimal extension of Markdown that explicitly encodes spans and hierarchical headers. Experiments across five state-of-the-art LLMs show that LTEM achieves accuracy comparable to HTML, offers a favorable accuracy-token trade-off relative to HTML and LaTeX, and produces substantially fewer invalid responses than LaTeX; for table generation, LTEM is comparable to MultiMarkdown though HTML is best. We release our taxonomy, benchmark, and format specification to support future research on LLM-table interaction.
| Comments: | Accepted to the EMNLP 2026 Main Conference |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29188 [cs.CL] |
| (or arXiv:2610.29188v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29188 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Eunbin Kim [view email]
[v1]
Wed, 21 Oct 2026 04:18:54 UTC (146 KB)
来源：arXiv cs.CL · arxiv.org