用表格让大模型更准地处理事实数据查询。
Talking with Tables for Better LLM Factual Data Interactions
- 在交互中引入表格结构提升信息定位能力。
- 平均性能提升40.29%，且更省计算资源。
- 适合需要精准数据操作的场景和研究者。
大型语言模型在处理现实场景中常见的信息检索与数据操作请求时表现不佳。本文证明，在与大模型交互时利用表格结构，比其他结构更能有效应对基于事实数据的常见请求。在多种场景和请求类型下的综合评估显示，提供表格结构可带来40.29%的平均性能提升，同时具备更强的鲁棒性和更高的令牌效率。通过注意力值分析发现，表格有助于模型更准确地定位相关信息，解释了性能提升的原因。我们还评估了在文本中融合结构化元素（如模板或属性固定顺序）以及知识图谱、JSON等其他结构的有效性，结果表明表格在效率与效果之间实现了最佳平衡。该方法对任务复杂度具有鲁棒性，并可通过文本转表格适配非结构化数据源。总体而言，本文揭示了表格表示在大模型未来应用中的巨大潜力。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often struggle with requests related to information retrieval and data manipulation that frequently arise in real-world scenarios under multiple conditions. In this paper, we demonstrate that leveraging tabular structures in LLM interactions, is more effective than utilizing other structures for handling prevalent requests that operate over factual data. Through comprehensive evaluations across various scenarios and request types, we show that providing tabular structures yields a 40.29\% average performance gain along with better robustness and token efficiency. Through attention-value analysis, we discover that tables help LLMs better locate relevant information, explaining these improvements. Beyond tables and text, we evaluate whether (1) blending structuredness within text, such as providing templates or fixing the order of attributes, and (2) other representative structures, such as knowledge graphs and JSON are helpful. We observe that utilizing tables offers the best balance between efficiency and effectiveness. The method remains robust to task complexity and adapts to unstructured sources through text-to-table conversion. Overall, we highlight the untapped potential of tabular representations for future LLM applications.
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。