让大模型学会在表格中回答概率性问题，提升不确定性推理能力。
Towards Probabilistic Question Answering Over Tabular Data
- 从表格构建贝叶斯网络，将自然语言转为概率查询
- 在新基准LUCARIO上显著优于基线方法
- 适合需要处理不确定性的数据分析场景
现有表格问答系统（如NL2SQL）在直接查表的常识性问题上表现良好，但在需在不确定性下进行推理的概率性问题上表现不佳。本文提出新基准LUCARIO及一套概率问答框架：从表格中推导贝叶斯网络，将自然语言查询转化为概率查询，并利用大语言模型生成最终答案。实验结果表明，该方法显著优于基线模型，凸显了符号与神经结合推理的优势。
原文摘要 · Abstract (English)
Current approaches for question answering (QA) over tabular data, such as NL2SQL systems, perform well for factual questions where answers are directly retrieved from tables. However, they fall short on probabilistic questions requiring reasoning under uncertainty. In this paper, we introduce a new benchmark LUCARIO and a framework for probabilistic QA over large tabular data. Our method induces Bayesian Networks from tables, translates natural language queries into probabilistic queries, and uses large language models (LLMs) to generate final answers. Empirical results demonstrate significant improvements over baselines, highlighting the benefits of hybrid symbolic-neural reasoning.
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。