通过自归纳与相关性重估改进规则检索与推理
Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate
AI总结：
针对规则检索中查询事实与规则抽象表示存在语义鸿沟导致准确率低的问题，提出自归纳增强检索SIAR和规则相关性重估R³方法，有效提升检索与推理效果。
摘要：
本文系统性地解决了规则检索领域的挑战，该领域至关重要却尚未得到充分研究。使用稀疏或稠密检索器直接搜索相关规则以支撑下游推理的常规检索方法，往往准确率较低。这主要是由于查询中的实例化事实与规则的抽象表示之间存在显著的语义鸿沟。这种错位会导致检索质量欠佳，进而对推理性能产生负面影响。为克服这些挑战，我们提出了自归纳增强检索（Self-Induction Augmented Retrieval，SIAR），这是一种利用大语言模型（Large Language Models，LLMs）的新方法，通过抽象查询中的底层知识与逻辑结构，归纳出可能对推理有益的潜在推理规则。随后将这些归纳出的规则用于查询增强，以提升检索效果。此外，我们还提出了规则相关性重估（Rule Relevance ReEstimate，R$^3$），该方法通过评估检索到的规则所包含的抽象知识能否被实例化以匹配查询中的事实、以及对推理的助益程度，来重估这些规则的相关性。在多种设置下开展的大量实验证明了我们所提方法的有效性与通用性。
英文摘要：
This paper systematically addresses the challenges of rule retrieval, a crucial yet underexplored area. Vanilla retrieval methods using sparse or dense retrievers to directly search for relevant rules to support downstream reasoning, often suffer from low accuracy. This is primarily due to a significant semantic gap between the instantiated facts in the queries and the abstract representations of the rules. Such misalignment results in suboptimal retrieval quality, which in turn negatively impacts reasoning performance. To overcome these challenges, we propose Self-Induction Augmented Retrieval (SIAR), a novel approach that utilizes Large Language Models (LLMs) to induce potential inferential rules that might offer benefits for reasoning by abstracting the underlying knowledge and logical structure in queries. These induced rules are then used for query augmentation to improve retrieval effectiveness. Additionally, we introduce Rule Relevance ReEstimate (R$^3$), a method that re-estimates the relevance of retrieved rules by assessing whether the abstract knowledge they contain can be instantiated to align with the facts in the queries and the helpfulness for reasoning. Extensive experiments across various settings demonstrate the effectiveness and versatility of our proposed methods.
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。
