用强化学习提升表格推理能力，效果超越主流大模型。
Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
- 采用规则奖励机制的强化学习，替代传统模仿学习。
- 在多个基准上超越监督微调，7B模型文本转SQL达68.3%。
- 通用训练让模型更鲁棒，适合需要精确推理的应用。
表格推理涵盖表格问答、事实验证和文本转SQL等任务，需精准理解结构化数据并进行数值计算与代码操作。监督微调（SFT）虽取得显著成果，但因模仿学习固有偏差，常面临泛化与鲁棒性不足问题。本文提出首个将强化学习（RL）应用于表格推理的方法——Reasoning-Table，通过严谨的数据预处理、奖励设计与定制训练策略，利用简单规则奖励实现性能超越。统一多任务训练使模型具备强泛化能力，在多个基准上表现领先，7B模型在BIRD开发集上达到68.3%的文本转SQL准确率，优于更大的专有模型Claude-3.7-Sonnet 4.0%。实验还证明其在泛化与鲁棒性方面的优势。
原文摘要 · Abstract (English)
Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL) to table reasoning, achieving state-of-the-art performance. Through rigorous data preprocessing, reward design, and tailored training strategies, our method leverages simple rule-based outcome rewards to outperform SFT across multiple benchmarks. Unified training across diverse tasks enables Reasoning-Table to emerge as a robust table reasoning large language model, surpassing larger proprietary models like Claude-3.7-Sonnet by 4.0% on table reasoning benchmarks. The approach also achieves excellent performance on text-to-SQL tasks, reaching 68.3% performance on the BIRD dev dataset with a 7B model. Further experiments demonstrate that Reasoning-Table enhances the model's generalization capabilities and robustness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。