arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.03393cs.AI
收藏

TABQAWORLD: 优化多模态推理以实现多轮表格问答

TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering

University of California, Los Angeles（加州大学洛杉矶分校）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；SimpleWay

Tung Sum Thomas Kwok, Xinyu Wang, Xiaofeng Lin, Peng Lu, Chunhe Wang, Changlun Li, Hanwei Wu, Nan Tang, Elisa Kreiss, Guang Cheng

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

TABQAWORLD通过联合优化表格表示与估计，提升多轮表格问答的可靠性与效率，实现4.87%的准确率提升和33.35%的推理延迟降低。

摘要：

多模态推理已成为增强推理模型推理能力的强大框架。尽管多轮表格推理方法通过工具使用和奖励建模提升了推理准确性，但其依赖固定文本序列进行表格状态读取，导致表征误差在多次回合中显著累积。此类累积通过表格 grounding 方法缓解，但以推理计算和成本为代价，使实际部署变得不切实际。为了解决这一问题，我们引入TABQAWORLD，一个表格推理框架，通过联合优化表格动作的表示与估计。在表示方面，TABQAWORLD采用基于动作的多模态选择策略，动态切换视觉和文本表示以最大化表格状态读取的可靠性。在估计方面，TABQAWORLD通过表格元数据（包括维度、数据类型和关键值）优化分步推理轨迹，安全规划轨迹并压缩低复杂度动作以减少对话回合和延迟。设计为无需训练的框架，实验证明TABQAWORLD在基准上实现了4.87%的准确率提升，相对于静态设置，准确率提升5.42%，推理延迟降低33.35%，建立了可靠且高效的表格推理新标准。

英文摘要：

Multimodal reasoning has emerged as a powerful framework for enhancing reasoning capabilities of reasoning models. While multi-turn table reasoning methods have improved reasoning accuracy through tool use and reward modeling, they rely on fixed text serialization for table state readouts. This introduces representation errors in table encoding that significantly accumulate over multiple turns. Such accumulation is alleviated by tabular grounding methods in the expense of inference compute and cost, rendering real world deployment impractical. To address this, we introduce TABQAWORLD, a table reasoning framework that jointly optimizes tabular action through representation and estimation. For representation, TABQAWORLD employs an action-conditioned multimodal selection policy, which dynamically switches between visual and textual representations to maximize table state readout reliability. For estimation, TABQAWORLD optimizes stepwise reasoning trajectory through table metadata including dimension, data types and key values, safely planning trajectory and compressing low-complexity actions to reduce conversation turns and latency. Designed as a training-free framework, empirical evaluations show that TABQAWORLD achieves state-of-the-art performance with 4.87% accuracy improvements over baselines, with 5.42% accuracy gain and 33.35% inference latency reduction over static settings, establishing a new standard for reliable and efficient table reasoning.

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。

↑