用符号化结构提升LLM处理时间表格问答的鲁棒性
LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
- 将表格转为数据库模式，让LLM生成并执行SQL
- 在复杂查询上准确率提升，对表大小不敏感
- 适合需要可靠时序推理的应用场景
时间表格问答对大型语言模型（LLMs）构成重大挑战，需在结构化数据上进行稳健推理，传统提示方法常因记忆偏差、对表格规模敏感及复杂查询性能下降而失效。为此，我们提出TempTabQA-C合成数据集，用于系统化、可控评估，并引入符号化中间表示，将表格转换为数据库模式。该结构化方法使LLM能生成并执行SQL查询，增强泛化能力并缓解偏差。结合自适应少样本提示与上下文定制示例，方法在鲁棒性、可扩展性和性能上均表现更优。实验结果一致显示其在关键挑战上的显著改进，为基于LLM的稳健时序推理设立了新基准。
原文摘要 · Abstract (English)
Temporal tabular question answering presents a significant challenge for Large Language Models (LLMs), requiring robust reasoning over structured data, which is a task where traditional prompting methods often fall short. These methods face challenges such as memorization, sensitivity to table size, and reduced performance on complex queries. To overcome these limitations, we introduce TempTabQA-C, a synthetic dataset designed for systematic and controlled evaluations, alongside a symbolic intermediate representation that transforms tables into database schemas. This structured approach allows LLMs to generate and execute SQL queries, enhancing generalization and mitigating biases. By incorporating adaptive few-shot prompting with contextually tailored examples, our method achieves superior robustness, scalability, and performance. Experimental results consistently highlight improvements across key challenges, setting a new benchmark for robust temporal reasoning with LLMs.
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。