让大模型先找信息再作答，提升表格问答准确率
Seek and Solve Reasoning for Table Question Answering
- 设计寻解链式思维框架，分步引导模型找信息、答问题
- 在多个TQA数据集上性能超越基线，最高提升12.3个百分点
- 适合需要精准理解表格逻辑的复杂问答场景
表格结构与问题逻辑的复杂性使基于大语言模型（LLM）的表格问答（TQA）任务具有挑战性，通常需先进行任务简化才能求解。本文发现，任务简化过程中的推理能力比简化结果本身更具价值，因此提出一种「寻解」（Seek-and-Solve）流水线，指导LLM先寻找相关信息，再回答问题，并将两阶段在推理层面整合为统一的寻解链式思维（SS-CoT）。此外，我们从该流程中提炼出单步问答提示，利用带有SS-CoT路径的示范，在上下文学习（In-Context Learning）设置下引导模型解决复杂TQA任务。实验表明，该方法显著提升性能与可靠性，同时保持高效。研究强调了激发LLM推理能力对有效处理复杂TQA任务的重要性。
原文摘要 · Abstract (English)
The complexities of table structures and question logic make table-based question answering (TQA) tasks challenging for Large Language Models (LLMs), often requiring task simplification before solving. This paper reveals that the reasoning process during task simplification may be more valuable than the simplified tasks themselves and aims to improve TQA performance by leveraging LLMs' reasoning capabilities. We propose a Seek-and-Solve pipeline that instructs the LLM to first seek relevant information and then answer questions, integrating these two stages at the reasoning level into a coherent Seek-and-Solve Chain of Thought (SS-CoT). Additionally, we distill a single-step TQA-solving prompt from this pipeline, using demonstrations with SS-CoT paths to guide the LLM in solving complex TQA tasks under In-Context Learning settings. Our experiments show that our approaches result in improved performance and reliability while being efficient. Our findings emphasize the importance of eliciting LLMs' reasoning capabilities to handle complex TQA tasks effectively.
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。