用自举方法自动生成推理程序，减少人工标注。
BOOST: Bootstrapping Strategy-Driven Reasoning Programs for Program-Guided Fact-Checking
- 通过批判-修正循环自动生成推理程序示范
- 在复杂事实核查任务中，零样本和少样本表现均优于基线
- 适合需要可解释性推理的自动化审核场景
大型语言模型流水线提升了复杂声明的自动化事实核查能力，但许多方法依赖需大量人力和领域知识的少样本上下文学习示范。其中，程序引导推理通过将声明分解为函数调用并执行推理程序，展现出显著潜力，但仍受限于手工编写示范。本质上，高效推理程序生成的底层原理仍待探索。本文提出BOOST，一种用于自动化少样本推理程序生成的自举方法。该方法通过批判-修正循环迭代优化显式的、数据驱动的元规则，指导示范生成，无需人工干预。这实现了从零样本到少样本程序引导学习的无缝过渡，提升了可解释性和有效性。实验结果表明，BOOST在复杂声明验证任务中，无论在零样本还是少样本设置下，均优于现有基线。
原文摘要 · Abstract (English)
Large language model pipelines have improved automated fact-checking for complex claims, yet many approaches rely on few-shot in-context learning with demonstrations that require substantial human effort and domain expertise. Among these, program-guided reasoning, by decomposing claims into function calls and executing reasoning programs, which has shown particular promise, but remains limited by the need for manually crafted demonstrations. Fundamentally, the underlying principles of effective reasoning program generation still remain underexplored. In this work, we introduce BOOST, a bootstrapping approach for automated few-shot reasoning program generation. BOOST iteratively refines explicit, data-driven guidelines as meta-rules for guiding demonstration creation, using a critique-refine loop that eliminates the need for human intervention. This enables a seamless transition from zero-shot to few-shot program-guided learning, enhancing interpretability and effectiveness. Experimental results show that BOOST outperforms prior few-shot baselines in both zero-shot and few-shot settings for complex claim verification.
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。