用推理时扩展提升表格推理能力，7B模型媲美GPT-4
Table-R1: Inference-Time Scaling for Table Reasoning
- 通过大模型推理轨迹蒸馏和可验证奖励强化学习实现推理时扩展
- 7B模型在多个任务上达到甚至超过GPT-4.1和DeepSeek-R1性能
- 适合关注小模型高推理效率与泛化能力的研究者
本文首次研究表格推理任务中的推理时扩展。提出两种后训练策略：基于前沿模型推理轨迹的蒸馏，以及基于可验证奖励的强化学习（RLVR）。针对蒸馏，构建了由DeepSeek-R1生成的大规模推理轨迹数据集，用于微调得到Table-R1-SFT模型；针对RLVR，设计任务特定的可验证奖励函数，并采用GRPO算法训练出Table-R1-Zero模型。在短答案问答、事实验证和自由问答等多样化表格推理任务上评估，结果表明，仅使用70亿参数的Table-R1-Zero模型在性能上匹配或超越GPT-4.1和DeepSeek-R1，且在跨领域数据集上展现强泛化能力。消融实验与定性分析揭示指令微调、模型架构选择及跨任务泛化的优势，以及强化学习训练中表推理核心技能的涌现。
原文摘要 · Abstract (English)
In this work, we present the first study to explore inference-time scaling on table reasoning tasks. We develop and evaluate two post-training strategies to enable inference-time scaling: distillation from frontier model reasoning traces and reinforcement learning with verifiable rewards (RLVR). For distillation, we introduce a large-scale dataset of reasoning traces generated by DeepSeek-R1, which we use to fine-tune LLMs into the Table-R1-SFT model. For RLVR, we propose task-specific verifiable reward functions and apply the GRPO algorithm to obtain the Table-R1-Zero model. We evaluate our Table-R1-series models across diverse table reasoning tasks, including short-form QA, fact verification, and free-form QA. Notably, the Table-R1-Zero model matches or exceeds the performance of GPT-4.1 and DeepSeek-R1, while using only a 7B-parameter LLM. It also demonstrates strong generalization to out-of-domain datasets. Extensive ablation and qualitative analyses reveal the benefits of instruction tuning, model architecture choices, and cross-task generalization, as well as emergence of essential table reasoning skills during RL training.
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。