# The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era

arXiv: https://arxiv.org/abs/2608.28980 · HTML: https://mlsanity.com/paper/2608.28980/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 84 of its 111 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 30 of 84)

- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [BLINK: Multimodal Large Language Models Can See but Not Perceive](https://mlsanity.com/paper/2404.12390/) (2024)
- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Can Language Models Solve Graph Problems in Natural Language?](https://mlsanity.com/paper/2305.10037/) (2023)
- [GraphGPT: Graph Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2310.13023/) (2023)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [LLaGA: Large Language and Graph Assistant](https://mlsanity.com/paper/2402.08170/) (2024)
- [Time Travel in LLMs: Tracing Data Contamination in Large Language Models](https://mlsanity.com/paper/2308.08493/) (2023)
- [Talk like a Graph: Encoding Graphs for Large Language Models](https://mlsanity.com/paper/2310.04560/) (2023)
- [Are Language Models Actually Useful for Time Series Forecasting?](https://mlsanity.com/paper/2406.16964/) (2024)

## Abstract (arXiv)

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.