arXiv cs.CL· Jinxiang Xie, Zihao Li, Rui Ding, Bartuer Zhou, Shi Han, Dongmei Zhang·· 14 小时前AI 评分34
面向 LLM 智能体时代数据分析的可扩展文本分析语义原子
Semantic Atoms for Scalable Text Analysis in Data Analytics in the Era of LLM-Based Agents
AI 导读
研究者提出 TADA-Agent，用 Tagging 和 Categorization 两种查询驱动的语义原子处理文本列，原子在生成的 Python 程序内运行并自动处理超出可靠上下文窗口的输入。在包含 40 个完整分析请求的 TABench 上，其行级语义质量与语义算子基线相当，完整产物保留估计更高，语义模型请求数少一个数量级以上。
正文 · 原文
Abstract:Much of the information needed for data analysis is buried in text columns: an analyst may infer customer frustration from complaint text and use it to explain resolution time. We call workloads in which processing text columns is central to subsequent data analysis TADA (\emph{Text Analysis in Data Analytics}). In an agentic setting, the user's query dynamically specifies this processing, and answering it interleaves LLM-based semantic steps with exact SQL or Python operations. This mixed execution raises two design questions: which work should be neural and which symbolic, and which semantic outputs later steps can reuse. We address them for agent-planned TADA workflows with two complementary, query-driven semantic atoms. Each atom takes a sequence of text items and a natural-language query specifying the semantic task: \textbf{Tagging} returns one string per input item, while \textbf{Categorization} returns $M$ category objects over $N$ input items. Tagging results are materialized as a row-aligned column and Categorization results as a category table; SQL or Python then performs exact computation over this exposed state. We realize this interface in TADA-Agent, whose atoms run inside generated Python programs and internally handle inputs beyond a reliable context window. We evaluate TADA-Agent on TABench, a benchmark of 40 complete analysis requests over spreadsheet tables spanning workflow composition, input--output structure, and literature-grounded analytical scenarios. Against a semantic-operator baseline and relative to a held-out TADA reference run, TADA-Agent delivers comparable row-level semantic quality, has higher complete-artifact preservation estimates, and uses over an order of magnitude fewer semantic-model requests under the evaluated native execution paths.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.34860 [cs.CL] |
| (or arXiv:2610.34860v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34860 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jinxiang Xie [view email]
[v1]
Mon, 26 Oct 2026 05:24:00 UTC (106 KB)
来源：arXiv cs.CL · arxiv.org