# ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold

arXiv: https://arxiv.org/abs/2604.13392 · HTML: https://mlsanity.com/paper/2604.13392/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 18 of 18)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization](https://mlsanity.com/paper/2501.03262/) (2025)
- [Why do tree-based models still outperform deep learning on tabular data?](https://mlsanity.com/paper/2207.08815/) (2022)
- [LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks](https://mlsanity.com/paper/2206.06565/) (2022)
- [Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2402.13950/) (2024)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales](https://mlsanity.com/paper/2312.07399/) (2023)
- [TABLET: Learning From Instructions For Tabular Data](https://mlsanity.com/paper/2304.13188/) (2023)
- [DNF-Net: A Neural Architecture for Tabular Data](https://mlsanity.com/paper/2006.06465/) (2020)
- [DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization](https://mlsanity.com/paper/2505.12366/) (2025)
- [InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation](https://mlsanity.com/paper/2406.00426/) (2024)
- [Strengthening LLMs for Tabular Prediction with Structural Priors](https://mlsanity.com/paper/2510.17385/) (2025)
- [TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data Prediction](https://mlsanity.com/paper/2505.21807/) (2025)

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

- [BoostLLM: Boosting-inspired LLM Fine-tuning for Few-shot Tabular Classification](https://mlsanity.com/paper/2605.06117/) (2026)

## Abstract (arXiv)

Tabular data remains prevalent in high-stakes domains such as healthcare and finance, where predictive models are expected to provide both high accuracy and faithful, human-understandable reasoning. While symbolic models offer verifiable logic, they lack semantic expressiveness. Meanwhile, general-purpose LLMs often require specialized fine-tuning to master domain-specific tabular reasoning. To address the dual challenges of scalable data curation and reasoning consistency, we propose ReSS, a systematic framework that bridges symbolic and neural reasoning models. ReSS leverages a decision-tree model to extract instance-level decision paths as symbolic scaffolds. These scaffolds, alongside input features and labels, guide an LLM to generate grounded natural-language reasoning that strictly adheres to the underlying decision logic. The resulting high-quality dataset is used to fine-tune a pretrained LLM into a specialized tabular reasoning model, further enhanced by a scaffold-invariant data augmentation strategy to improve generalization and explainability. To rigorously assess faithfulness, we introduce quantitative metrics including hallucination rate, explanation necessity, and explanation sufficiency. Experimental results on medical and financial benchmarks demonstrate that ReSS-trained models improve traditional decision trees and standard fine-tuning approaches up to 10% while producing faithful and consistent reasoning