arXiv cs.AI· G\"unther Schindler, Maximilian Schambach, Johannes H\"ohne·· 6 天前AI 评分29
CASE：用上下文感知语义嵌入增强表格学习器
Enhancing Tabular Learners with Context-Aware Semantic Embeddings
AI 导读
研究者提出 CASE（Context-Aware Semantic Embeddings）框架，将 LLM 的语义理解与表格学习器的统计能力结合。CASE 用数据集代表性行样本预填充基于 Gemma 3 定制训练的表格语言模型 KV cache，使生成的行嵌入动态上下文化。
正文 · 原文
Abstract:While modern tabular learners excel at capturing statistical patterns, they frequently operate in a semantic vacuum, treating textual features as discrete symbols, ignoring the rich semantics inherent in feature names or cell entries. We propose CASE (Context-Aware Semantic Embeddings), a novel framework that bridges the gap between the semantic understanding of Large Language Models (LLMs) and the statistical capabilities of tabular learners. Unlike existing methods that embed rows in isolation, CASE utilizes a contextualization strategy: we pre-fill the KV cache of a custom-trained Gemma 3-based Tabular Language Model with a representative sample of rows to establish a persistent anchor of the dataset's semantics. This ensures that generated row embeddings are dynamically contextualized, resolving semantic ambiguities and anchoring representations in domain-specific context. Our experiments across several benchmarks (CARTE, TextTab, and TabArena) demonstrate that CASE substantially improves the performance of tabular learners on semantically rich datasets, particularly in low-data regimes.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2608.03565 [cs.AI] |
| (or arXiv:2608.03565v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.03565 arXiv-issued DOI via DataCite |
Submission history
From: Günther Schindler [view email]
[v1]
Tue, 4 Aug 2026 12:29:37 UTC (3,006 KB)
[v2]
Fri, 9 Oct 2026 10:55:21 UTC (976 KB)
来源：arXiv cs.AI · arxiv.org