无需参考表，用图推理评估大模型生成表格的质量。
TabReX : Tabular Referenceless eXplainable Evaluation
- 将文本和表格转为知识图谱，通过LLM对齐评估结构与事实一致性。
- 在六个领域、十二种扰动下，与专家评分相关性最高，稳定性强。
- 可生成逐单元错误定位，适合需可信解释的表格生成研究者。
评估大语言模型生成表格的质量仍面临挑战：现有指标要么将表格扁平化为文本，忽略结构；要么依赖固定参考，限制泛化能力。我们提出TabReX，一种无参考、基于属性的表格生成评估框架，采用图式推理实现。TabReX将源文本与生成表格均转换为规范知识图谱，通过LLM引导的匹配过程对齐，并计算可解释、符合评分标准的得分，量化结构与事实保真度。该度量支持敏感性与特异性之间的可控权衡，生成与人类判断一致的结果及单元级错误追踪。为系统评估度量鲁棒性，我们构建了涵盖六个领域、十二种规划驱动扰动类型、三类难度层级的TabReX-Bench大规模基准。实证结果表明，TabReX在专家评分中相关性最高，在更复杂扰动下仍保持稳定，并支持细粒度的模型-提示对比分析，确立了可信、可解释的结构化生成评估新范式。
原文摘要 · Abstract (English)
Evaluating the quality of tables generated by large language models (LLMs) remains an open challenge: existing metrics either flatten tables into text, ignoring structure, or rely on fixed references that limit generalization. We present TabReX, a reference-less, property-driven framework for evaluating tabular generation via graph-based reasoning. TabReX converts both source text and generated tables into canonical knowledge graphs, aligns them through an LLM-guided matching process, and computes interpretable, rubric-aware scores that quantify structural and factual fidelity. The resulting metric provides controllable trade-offs between sensitivity and specificity, yielding human-aligned judgments and cell-level error traces. To systematically asses metric robustness, we introduce TabReX-Bench, a large-scale benchmark spanning six domains and twelve planner-driven perturbation types across three difficulty tiers. Empirical results show that TabReX achieves the highest correlation with expert rankings, remains stable under harder perturbations, and enables fine-grained model-vs-prompt analysis establishing a new paradigm for trustworthy, explainable evaluation of structured generation systems.
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。