mlsanityData to 14 Oct 2026

TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data Prediction

arXiv 2505.21807 ↗First posted 27 May 2025cs.LGcited by 1

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Predictive modeling on tabular data is the cornerstone of many real-world applications. Although gradient boosting machines and some recent deep models achieve strong performance on tabular data, they often lack interpretability. On the other hand, large language models (LLMs) have demonstrated powerful capabilities to generate human-like reasoning and explanations, but remain under-performed for tabular data prediction. In this paper, we propose a new approach that leverages reasoning-based LLMs, trained using reinforcement learning, to perform more accurate and explainable predictions on tabular data. Our method introduces custom reward functions that guide the model not only toward better prediction accuracy but also toward human-understandable reasons for its predictions. The proposed method is evaluated on financial benchmark datasets and compared against established LLMs.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 17 of its 20 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

17 of 20 references.

References · 17

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  6. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  7. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  8. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  9. 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 277
  10. 2023PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Financecited by 222
  11. 2024FinBen: A Holistic Financial Benchmark for Large Language Modelscited by 141
  12. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
5 more
  1. 2024Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Modelscited by 36
  2. 2024Open-FinLLMs: Open Multimodal Large Language Models for Financial Applicationscited by 36
  3. 2023Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Modelscited by 24
  4. 2023FinPT: Financial Risk Prediction with Profile Tuning on Pretrained Foundation Modelscited by 13
  5. 2024Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretrainingcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffoldcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding
  2. 2025Strengthening LLMs for Tabular Prediction with Structural Priors
  3. 2025TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
  4. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning
  5. 2026TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction
  6. 2025How well do LLMs reason over tabular data, really?
  7. 2025Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning
  8. 2025Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning