用于引导大语言模型多步推理的图启发方法
Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models
AI总结：
针对大语言模型直接生成子问题易冗余无关的问题，提出GE-Reasoning方法，通过生成带变量的知识三元组构建问题图表示，结合检索生成子问题并按置信度筛选，在多跳问答基准上优于现有CoT类方法。
摘要：
思维链（Chain-of-Thought, CoT）提示结合子问题生成与解答已提升了大语言模型（Large Language Models, LLMs）的多步推理能力。然而，提示LLMs直接生成子问题的效果并非最优，因为它们有时会生成冗余或无关的问题。针对这一问题，我们提出GE-Reasoning方法，引导LLMs生成恰当的子问题及对应答案。具体而言，给定输入问题，我们首先提示LLM生成知识三元组，构建该问题的图表示。与传统知识三元组不同，我们的方法允许变量作为头实体或尾实体，可有效将问题表示为知识三元组。其次，针对每个三元组，LLM结合知识检索生成对应的子问题与答案。若预测置信度超过阈值，则将该子问题与预测结果纳入提示中用于后续处理。该方法确保子问题基于提取的知识三元组生成，减少了冗余性与无关性。我们的实验表明，该方法在多跳问答基准数据集上的表现优于以往的CoT提示方法及其变体。
英文摘要：
Chain-of-Thought (CoT) prompting along with sub-question generation and answering has enhanced multi-step reasoning capabilities of Large Language Models (LLMs). However, prompting the LLMs to directly generate sub-questions is suboptimal since they sometimes generate redundant or irrelevant questions. To deal with them, we propose a GE-Reasoning method, which directs LLMs to generate proper sub-questions and corresponding answers. Concretely, given an input question, we first prompt the LLM to generate knowledge triplets, forming a graph representation of the question. Unlike conventional knowledge triplets, our approach allows variables as head or tail entities, effectively representing a question as knowledge triplets. Second, for each triplet, the LLM generates a corresponding sub-question and answer along with using knowledge retrieval. If the prediction confidence exceeds a threshold, the sub-question and prediction are incorporated into the prompt for subsequent processing. This approach encourages that sub-questions are grounded in the extracted knowledge triplets, reducing redundancy and irrelevance. Our experiments demonstrate that our approach outperforms previous CoT prompting methods and their variants on multi-hop question answering benchmark datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
