发表机构
Beijing Normal University; Beijing Normal-Hong Kong Baptist University（北京师范大学; 北京师范大学-香港浸会大学联合国际学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出STQA基准，覆盖4,417只股票和31,400个问答对，评估历史与预测数据的表格问答，并引入SQFRS框架，发现预测推理是当前大模型的瓶颈。
AI 中文摘要
股票市场分析本质上需要对历史记录和未来预测进行复合推理，然而现有基准在孤立任务上仍然分散。我们提出了STQA（股票聚焦的表格问答），一个端到端的基准，旨在系统地评估对历史数据、数值预测和基于预测的推理的自然语言问答。基于大规模金融数据集，STQA覆盖4,417只股票，包含31,400个由专家设计的模板生成的问答对，并附有细粒度的意图和槽位标注。为使该基准可操作，我们提出了SQFRS（股票查询-预测-推理系统），一个基于智能体的统一框架，协调SQL检索和时间序列预测工具。实验表明，尽管当前大型语言模型在历史查询上表现良好，但基于预测的推理构成了重大挑战，揭示了工具协调和不确定性下推理的关键瓶颈。数据集和代码可在该https URL获取。因此，STQA为未来关于可信、工具增强的金融智能体的研究提供了严格的测试平台。
英文摘要
Stock market analysis inherently requires composite reasoning over historical records and future projections, yet existing benchmarks remain fragmented across isolated tasks. We introduce STQA (Stock-focused Tabular Question Answering), an end-to-end benchmark designed to systematically evaluate natural-language question answering over historical data, numerical forecasts, and forecast-based reasoning. Built on a large-scale financial dataset, STQA covers 4,417 stocks and contains 31,400 question-answer pairs derived from expert-crafted templates, accompanied by fine-grained intent and slot annotations. To operationalize this benchmark, we present SQFRS (Stock Query-Forecast-Reasoning System), an agent-based unified framework that orchestrates SQL retrieval and time-series forecasting tools. Experiments demonstrate that while current large language models perform well on historical queries, forecast-based reasoning poses a substantial challenge, revealing critical bottlenecks in tool coordination and reasoning under uncertainty. The dataset and code are available at https://github.com/xuxubaobaoan/STQA_Project. STQA thus serves as a rigorous testbed for future research on trustworthy, tool-augmented financial agents.
Comments9 pages of main text, 15 pages of appendices, 19 figures. Accepted to Findings of EMNLP 2026
