研究人员开发了两个用于改进表格数据处理的新框架。其中一个名为“通过表示稳定性提高表格检索的鲁棒性”（Improving Robustness of Tabular Retrieval via Representational Stability），通过平均不同格式的嵌入来创建规范表示，解决了基于Transformer的表格检索系统中的序列化敏感性问题。另一个框架SAGE（Sparse Adaptive Guidance）是一个基于LLM的框架，用于生成合成表格数据，它强制执行稀疏和动态依赖指导，提高了数据的保真度和下游效用。此外，还引入了一个名为TEmBed的基准测试，用于系统地评估各种任务和表示级别的表格嵌入，为选择合适的模型提供了实践指导。 AI
影响 用于表格数据检索和生成的新方法为下游任务提供了更高的保真度和效用。
排序理由 多篇学术论文在arXiv上发布，详细介绍了表格数据处理的新方法和基准测试。
AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →
arXiv:2604.24368v1 Announce Type: new Abstract: Generating high-fidelity synthetic tabular data remains a critical challenge for enhancing data availability in privacy-sensitive and low-resource domains. Recent approaches leverage LLMs by representing table rows as sequences, yet…
arXiv:2604.24040v1 Announce Type: new Abstract: Transformer-based table retrieval systems flatten structured tables into token sequences, making retrieval sensitive to the choice of serialization even when table semantics remain unchanged. We show that semantically equivalent ser…
Generating high-fidelity synthetic tabular data remains a critical challenge for enhancing data availability in privacy-sensitive and low-resource domains. Recent approaches leverage LLMs by representing table rows as sequences, yet suffer from two fundamental limitations: (1) th…
Transformer-based table retrieval systems flatten structured tables into token sequences, making retrieval sensitive to the choice of serialization even when table semantics remain unchanged. We show that semantically equivalent serializations, such as $\texttt{csv}$, $\texttt{ts…
arXiv:2604.22337v1 Announce Type: new Abstract: Most tabular-data generators match marginal statistics yet ignore causal structure, leading downstream models to learn spurious or unfair patterns. We present TabSCM, a mixed-type generator that preserves those causal dependencies. …
Most tabular-data generators match marginal statistics yet ignore causal structure, leading downstream models to learn spurious or unfair patterns. We present TabSCM, a mixed-type generator that preserves those causal dependencies. Starting from a Completed Partially Directed Acy…
Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as table retrieval, semantic search and table-based prediction. Despite the growing number of such models, it remains unclear which …