arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11700cs.LGcs.AI
收藏

TabSieve: 表格内证据选择用于表格预测

TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction

Yongyao Wang, Ziqi Miao, Lu Yang, Haonan Jia, Wenting Yan, Chen Qian, Lijun Li

AI总结:

TabSieve通过显式选择表格内证据提升预测性能,采用强化学习优化证据选择与预测正确性,实验显示在分类和回归任务中均取得显著提升。

摘要:

表格预测可以从表格内的行作为少样本证据获益,但现有的表格模型通常进行实例级推理,基于大语言模型的提示通常容易出错。模型并不一致地利用相关行,嘈杂的上下文会降低性能。为了解决这一挑战,我们提出了TabSieve,一种先选择后预测的框架,使证据使用变得明确且可审计。给定一个表格和一个查询行,TabSieve首先选择一小部分信息丰富的行作为证据,然后根据所选证据预测缺失的目标。为了实现这一能力,我们构建了TabSieve-SFT-40K,通过使用一个强大的教师模型和严格过滤,从331个真实表格中合成高质量的推理轨迹。此外,我们引入了TAB-GRPO,一种强化学习配方,通过单独的奖励共同优化证据选择和预测正确性,并通过动态任务优势平衡稳定混合回归和分类训练。在75个分类和52个回归表格的保留基准测试中,TabSieve在各种shot预算下都一致提高了性能,与第二好的基线相比,分类平均提高了2.92%,回归平均提高了4.45%。进一步分析表明,TabSieve更关注所选证据,这提高了对嘈杂上下文的鲁棒性。

英文摘要:

Tabular prediction can benefit from in-table rows as few-shot evidence, yet existing tabular models typically perform instance-wise inference and LLM-based prompting is often brittle. Models do not consistently leverage relevant rows, and noisy context can degrade performance. To address this challenge, we propose TabSieve, a select-then-predict framework that makes evidence usage explicit and auditable. Given a table and a query row, TabSieve first selects a small set of informative rows as evidence and then predicts the missing target conditioned on the selected evidence. To enable this capability, we construct TabSieve-SFT-40K by synthesizing high-quality reasoning trajectories from 331 real tables using a strong teacher model with strict filtering. Furthermore, we introduce TAB-GRPO, a reinforcement learning recipe that jointly optimizes evidence selection and prediction correctness with separate rewards, and stabilizes mixed regression and classification training via dynamic task-advantage balancing. Experiments on a held-out benchmark of 75 classification and 52 regression tables show that TabSieve consistently improves performance across shot budgets, with average gains of 2.92% on classification and 4.45% on regression over the second-best baseline. Further analysis indicates that TabSieve concentrates more attention on the selected evidence, which improves robustness to noisy context.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑