AI 中文总结
本文通过分析159篇跨9种模态的论文，发现基础模型时代专用机器学习模型未被替代，语言模型需补充结构组件，其与结构感知架构的性能差距能否消除仍待验证。
AI 中文摘要
机器学习传统上为结构化数据构建的专用架构能否被基于语言的模型替代？本文通过回顾2016至2026年跨9种模态的159篇论文，结合预测准确率、结构表征与计算能力对此问题展开研究。研究区分了完成任务与保留并计算使任务可处理的结构，将现有方法分为8种表征范式，涵盖仅语言系统到完全专用架构。结果显示，语言介导模型在特定场景（如极端少样本预测、离散符号任务、带文本注释的知识图谱、大规模单模态预训练）中极具竞争力；但当直接评估结构表征或计算能力而非仅准确率时，未发现通用架构被替代的证据。相反，不同研究领域均出现一种重复模式：当仅靠语言不足时，缺失的结构会通过图模块、结构token、专用注意力或其他非语言组件重新引入，即专用性更多是转移而非消失。此外，尽管语言模型的性能随规模扩大而提升，但其与结构感知架构的差距能否最终消除仍未得到验证。
英文摘要
Specialized machine learning architectures encode structural assumptions (equivariance, permutation invariance, relational structure) that language-based foundation models lack by design. This review asks whether such assumptions can instead be acquired through language, drawing on a corpus of 186 papers published between 2016 and 2026 across nine modalities: tabular data, graphs, time series, vision, chemistry, code, knowledge graphs, point clouds, and protein structure. Methods are organized into eight representational regimes, ranging from language-only prompting to fully specialized architectures, and are assessed not only on predictive accuracy but on whether structural information is preserved by the representation and computed by the model. Language-mediated models prove competitive in extreme few-shot prediction, discretized symbolic tasks, and textually annotated knowledge graphs. No evidence of general replacement survives once structure itself is evaluated: where direct tests exist, apparent parity is traceable to information asymmetry, benchmark contamination, or computation performed outside the language model. Across independent research communities, missing structural inductive biases are reintroduced through graph modules, structure-aware tokens, or specialized attention, indicating that specialization is relocated rather than eliminated. The review closes by specifying a falsifiable controlled experiment that would measure the remaining gap directly. The derived data supporting the findings of this review are openly available in the repository at https://github.com/kiyan-rezaee/language-vs-structure.
Comments75 pages, 11 tables, 6 figures
