检索增强语言模型中的溯因推理：生成与验证缺失前提
Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises
- Independent Researcher, Mountain View, CA94039, USA（独立研究者）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出将溯因推理集成到检索增强语言模型中，通过检测证据不足、生成并验证缺失前提，在多个基准上提升了答案准确性与推理忠实度。
AI中文摘要：
经过检索增强的大型语言模型（LLMs）——通常被称为检索增强生成（RAG）——在知识密集型任务中表现出了强大的性能。然而，当检索到的证据不完整时，RAG流程往往会出现失败，从而在推理过程中留下空白。在这种情况下，溯因推理——即生成合理的缺失前提以解释观察结果的过程——为弥合这些空白提供了一种有原则的方法。在本文中，我们提出了一个将溯因推理集成到检索增强LLMs中的框架。我们的方法检测证据不足的情况，生成候选缺失前提，并通过一致性和合理性检查对其进行验证。在溯因推理和多跳问答基准上的实验结果表明，我们的方法同时提高了答案准确性和推理忠实度。这项工作凸显了溯因推理作为增强RAG系统鲁棒性和可解释性的一个有前景的方向。
英文摘要：
Large Language Models (LLMs) enhanced with retrieval -- commonly referred to as Retrieval-Augmented Generation (RAG) -- have demonstrated strong performance in knowledge-intensive tasks. However, RAG pipelines often fail when retrieved evidence is incomplete, leaving gaps in the reasoning process. In such cases, \emph{abductive inference} -- the process of generating plausible missing premises to explain observations -- offers a principled approach to bridge these gaps. In this paper, we propose a framework that integrates abductive inference into retrieval-augmented LLMs. Our method detects insufficient evidence, generates candidate missing premises, and validates them through consistency and plausibility checks. Experimental results on abductive reasoning and multi-hop QA benchmarks show that our approach improves both answer accuracy and reasoning faithfulness. This work highlights abductive inference as a promising direction for enhancing the robustness and explainability of RAG systems.
