ALTER:面向大表格推理的增强方法
ALTER: Augmentation for Large-Table-Based Reasoning
AI总结:
ALTER框架通过查询增强器和表格增强器利用自然语言问题与半结构化表格中的潜在增强信息,仅使用少量相关数据即在大表格推理基准上超越现有方法,并表现出鲁棒性和高效性。
摘要:
尽管已有大量研究探索了使用大语言模型(LLMs)进行基于表格的推理,但大多数方法在应用于大表格时难以扩展。为了在这些场景中保持大语言模型卓越的理解能力,我们提出了ALTER(Augmentation for Large-Table-Based Reasoning)——一个旨在利用潜在增强能力的框架,既通过查询增强器利用自由形式自然语言(NL)问题中的增强潜力,也通过表格增强器利用半结构化表格数据中的增强潜力。通过仅利用表格中一小部分相关数据,并补充预先增强的模式、语义和字面信息,ALTER在基于表格的推理基准上取得了出色的性能。我们还对大表格场景进行了详细分析,比较了不同方法和各种划分原则。在这些场景中,我们的方法优于所有其他方法,并展现出对扰动的鲁棒性和高效性。
英文摘要:
While extensive research has explored the use of large language models (LLMs) for table-based reasoning, most approaches struggle with scalability when applied to large tables. To maintain the superior comprehension abilities of LLMs in these scenarios, we introduce ALTER(Augmentation for Large-Table-Based Reasoning)-a framework designed to harness the latent augmentation potential in both free-form natural language (NL) questions, via the query augmentor, and semi-structured tabular data, through the table augmentor. By utilizing only a small subset of relevant data from the table and supplementing it with pre-augmented schema, semantic, and literal information, ALTER achieves outstanding performance on table-based reasoning benchmarks. We also provide a detailed analysis of large-table scenarios, comparing different methods and various partitioning principles. In these scenarios, our method outperforms all other approaches and exhibits robustness and efficiency against perturbations.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。