---
title: "为什么大语言模型在表格预测上失败？"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.02412v1"
permalink: "https://feed.astralor.com/items/itm_6c5481fdddcae466b2803110"
published: "2026-08-03T15:52:51.000Z"
score: 78
channel: "ai"
tags: ["arXiv","大语言模型","维度诅咒","表格基础模型","表格预测"]
---

# 为什么大语言模型在表格预测上失败？

## AI 点评

> 这篇论文值得所有做表格学习的人读——它终于用严密的实验告诉我们，LLM在表格上不行不是‘不够努力’，而是维度一高就彻底失效。对表格基础模型研究者来说，这是一个必须攻克的信号；对工业界用户而言，换个方向可能比继续堆提示词更有效。

## 速览

本论文系统研究了大语言模型在表格数据预测任务上表现不佳的根本原因。通过严格控制变量的实验，排除了噪声、CSV格式、数值分词和批量预测等假设，发现维度是关键因素：随着数据维度增长，LLM准确率下降，而经典基线模型保持稳定甚至提升。行为对比显示，LLM在二维空间类似局部距离方法，但在高维下没有任何经典模型（即使加入维度相关噪声）能复现其预测。该发现解释了LLM为何在表格任务上输给传统模型，但内部机制仍待探索。

## 关键点

- 通过控制实验否定了噪声、CSV格式、分词和批量预测四类假设
- 维度是决定性因素：LLM准确率随维度增长而下降，而经典模型不受影响
- 二维下LLM预测与局部距离方法高度一致，高维下无经典模型可复现
- 研究将内部机制列为开放问题，提示需要更深入的可解释性分析

## 全文

Large language models (LLMs) have become the default tool for a remarkable range of tasks, yet they have had conspicuously little success at one of the most common machine learning workloads: predictive analytics over tabular data. This gap is the founding premise of the fast-growing field of tabular foundation models, but the question of why generic LLMs fail has remained open. We study a frontier LLM in its purest inference regime - a single generation pass over a prompt containing the full training and test data, with no tools, no agentic scaffolding, and no fine-tuning - and systematically evaluate five hypotheses for the failure: (a) an inability to handle noisy or non-linearly-separable data; (b) the linearised CSV format obscuring column structure; (c) the tokenisation of numeric values; (d) the number of test points classified per query; and (e) the dimensionality of the input. Controlled experiments falsify (a)-(d). Dimensionality, in contrast, is decisive: sweeping random linear projections of thirty-one benchmark datasets, the LLM is the only method among nine whose accuracy decreases as dimensionality grows, while every classical baseline stays flat or improves. A behavioural comparison against 252 configured classical models finds that in two dimensions the LLM predicts like a local, distance-based method (up to 91.6% grid agreement), but in higher dimensions no classical model - even when augmented with tuned, dimension-dependent noise - reproduces its predictions. We do not claim to have identified the internal mechanism; our results show, more modestly, that the LLM's capability dissolves with dimension in a way no noise-corrupted classical learner mimics - which explains why LLMs, so capable elsewhere, keep losing to fifty-year-old baselines on tables, while leaving the mechanism of the prediction as an open question.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_6c5481fdddcae466b2803110