ReSS is a framework that bridges symbolic and neural reasoning models for tabular data prediction, aiming for both high accuracy and understandable reasoning. It leverages decision trees to extract symbolic scaffolds that guide an LLM to generate natural-language reasoning, which is then used to fine-tune specialized tabular reasoning LLMs.
This research introduces "Schema-Adaptive Tabular Representation Learning," a novel method using Large Language Models (LLMs) to generate transferable tabular embeddings. By semantically encoding structured variables into natural language, it enables zero-shot alignment across varying EHR schemas in clinical medicine without manual feature engineering.
Geometry-Aware Tabular Diffusion (GATD) is introduced to improve tabular synthesis by augmenting denoisers with pairwise angles and lengths computed from column value differences. It achieves state-of-the-art performance with fewer parameters, reducing Shape and Trend error, and showing that explicit relational supervision drives the gains.