arXiv cs.CL· Baowen Zhang, Hangting Ye, Hongyuan Zha·· 3 天前AI 评分32
表格数据上的类型化决策模型研究
Typed Decision Models on Tabular Data
AI 导读
研究在表格数据上对比四种类型化决策模型与三个 LLM，覆盖行分类、事实核查和异常检测任务。每个请求以原始形式及 21 种保持内容不变的改写形式发送，决策模型以更低成本达到与 LLM 相当的表现，其中三个对问题表述方式远为稳健。但所有模型对表格组织方式都不稳健，至少三分之一的决策会因表格或问题的某种改写而改变，低概率决策最易变化。
正文 · 原文
Abstract:Typed decision models are language models that answer a question with a fixed set of possible answers by returning a probability for each answer instead of generating text. We study them on tabular data and compare four decision models with three large language models (LLMs) on row classification, fact verification and anomaly detection. Every request is sent in its original form and under 21 types of rewrite that keep its content, such as renaming the options or writing the table in another format. The decision models perform as well as the LLMs at a lower cost. Three of them are also far more robust to how the question is formulated. No model we test is robust to how the table is organized. For every model, at least a third of the row decisions change under some rewrite of the table or the question. The decisions to which a decision model gives low probability are the ones most likely to change. Decision models are a practical choice for tabular decisions, but their robustness remains an open problem.
| Comments: | 22 pages, 9 figures, 19 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.19536 [cs.CL] |
| (or arXiv:2610.19536v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19536 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Baowen Zhang [view email]
[v1]
Wed, 14 Oct 2026 03:54:19 UTC (420 KB)
来源：arXiv cs.CL · arxiv.org