# Schema-Adaptive Tabular Representation Learning with LLMs for Generalizable Multimodal Clinical Reasoning

arXiv: https://arxiv.org/abs/2604.11835 · HTML: https://mlsanity.com/paper/2604.11835/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 9 of its 47 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 9 of 9)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records](https://mlsanity.com/paper/2203.03540/) (2022)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [PTab: Using the Pre-trained Language Model for Modeling Tabular Data](https://mlsanity.com/paper/2209.08060/) (2022)
- [LLM Embeddings for Deep Learning on Tabular Data](https://mlsanity.com/paper/2502.11596/) (2025)
- [An Effective Deployment of Contrastive Learning in Multi-label Text Classification](https://mlsanity.com/paper/2212.00552/) (2022)
- [TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning](https://mlsanity.com/paper/2506.08646/) (2025)
- [Multi-Label Contrastive Learning : A Comprehensive Study](https://mlsanity.com/paper/2412.00101/) (2024)

## Built on by (most cited first, 1 of 1)

- [Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols](https://mlsanity.com/paper/2608.31014/) (2026)

## Abstract (arXiv)

Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine, where electronic health record (EHR) schemas vary significantly. To solve this problem, we propose Schema-Adaptive Tabular Representation Learning, a novel method that leverages large language models (LLMs) to create transferable tabular embeddings. By transforming structured variables into semantic natural language statements and encoding them with a pretrained LLM, our approach enables zero-shot alignment across unseen schemas without manual feature engineering or retraining. We integrate our encoder into a multimodal framework for dementia diagnosis, combining tabular and MRI data. Experiments on NACC and ADNI datasets demonstrate state-of-the-art performance and successful zero-shot transfer to unseen schemas, significantly outperforming clinical baselines, including board-certified neurologists, in retrospective diagnostic tasks. These results validate our LLM-driven approach as a scalable, robust solution for heterogeneous real-world data, offering a pathway to extend LLM-based reasoning to structured domains.