Fortune: Formula-Driven Reinforcement Learning for Symbolic Table Reasoning in Language Models

2025-05-29 · Lang Cao, Jingxian Xu, Hanbing Liu, Jinyu Wang, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang

Tables are a fundamental structure for organizing and analyzing data, making effective table understanding a critical capability for intelligent systems. While large language models (LMs) demonstrate strong general reasoning abilities, they continue to struggle with accurate numerical or symbolic reasoning over tabular data, especially in complex scenarios. Spreadsheet formulas provide a powerful and expressive medium for representing executable symbolic operations, encoding rich reasoning patterns that remain largely underutilized. In this paper, we propose Formula Tuning (Fortune), a reinforcement learning (RL) framework that trains LMs to generate executable spreadsheet formulas for question answering over general tabular data. Formula Tuning reduces the reliance on supervised formula annotations by using binary answer correctness as a reward signal, guiding the model to learn formula derivation through reasoning. We provide a theoretical analysis of its advantages and demonstrate its effectiveness through extensive experiments on seven table reasoning benchmarks. Formula Tuning substantially enhances LM performance, particularly on multi-step numerical and symbolic reasoning tasks, enabling a 7B model to outperform O1 on table understanding. This highlights the potential of formula-driven RL to advance symbolic table reasoning in LMs.

📄 PDF Abstract BibTeX arXiv:2505.23667

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering Reinforcement Learning (RL)

BaziQA-Benchmark: Evaluating Symbolic and Temporally Compositional Reasoning in Large Language Models

2026-02-13 · Jiangxi Chen, Qian Liu arxiv

We present BaziQA-Benchmark, a standardized benchmark for evaluating symbolic and temporally compositional reasoning in large language models. The benchmark is derived from 200 professionally curated, multiple-choice pro…

Beyond Error-Based Optimization: Experience-Driven Symbolic Regression with Goal-Conditioned Reinforcement Learning

2026-01-21 · Jianwen Sun, Xinrui Li, Fuqing Li, Xiaoxuan Shen arxiv

Symbolic Regression aims to automatically identify compact and interpretable mathematical expressions that model the functional relationship between input and output variables. Most existing search-based symbolic regress…

Reinforcement Learning

Deep Symbolic Optimization: Reinforcement Learning for Symbolic Mathematics

2025-05-16 · Conor F. Hayes, Felipe Leno Da Silva, Jiachen Yang, T. Nathan Mundhenk 외

Deep Symbolic Optimization (DSO) is a novel computational framework that enables symbolic optimization for scientific discovery, particularly in applications involving the search for intricate symbolic structures. One no…

Equation Discovery reinforcement-learning Reinforcement Learning scientific discovery+1

Reinforced Symbolic Learning with Logical Constraints for Predicting Turbine Blade Fatigue Life

2024-11-18 · Pei Li, Joo-Ho Choi, Dingyang Zhang, Shuyou Zhang 외

Accurate prediction of turbine blade fatigue life is essential for ensuring the safety and reliability of aircraft engines. A significant challenge in this domain is uncovering the intrinsic relationship between mechanic…

Deep Reinforcement Learning Symbolic Regression

SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning

2018-10-31 · Daoming Lyu, Fangkai Yang, Bo Liu, Steven Gustafson

Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of the subtasks is critical in hie…

Decision Making Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+2