Abstract
Retrieval-augmented generation (RAG) systems have been widely adopted in contemporary large language models (LLMs) due to their ability to improve generation quality while reducing the required input context length. In this work, we focus on RAG systems for long-document question answering. Current approaches suffer from a heavy reliance on LLM descriptions resulting in high resource consumption and latency, repetitive content across hierarchical levels, and hallucinations due to no or limited grounding in the source text. To improve both efficiency and factual accuracy through grounding, we propose GroundedKG-RAG, a RAG system in which the knowledge graph is explicitly extracted from and grounded in the source document. Specifically, we define nodes in GroundedKG as entities and actions, and edges as temporal or semantic relations, with each node and edge grounded in the original sentences. We construct GroundedKG from semantic role labeling (SRL) and abstract meaning representation (AMR) parses and then embed it for retrieval. During querying, we apply the same transformation to the query and retrieve the most relevant sentences from the grounded source text for question answering. We evaluate GroundedKG-RAG on examples from the NarrativeQA dataset and find that it performs on par with a state-of-the art proprietary long-context model at smaller cost and outperforms a competitive baseline. Additionally, our GroundedKG is interpretable and readable by humans, facilitating auditing of results and error analysis.
Abstract (translated)
检索增强生成（RAG）系统因其能在提升生成质量的同时减少所需输入上下文长度，已被广泛应用于当代大语言模型（LLMs）中。本研究聚焦于长文档问答场景下的RAG系统。当前方法存在严重依赖大语言模型自身描述导致资源消耗高、延迟大，层级间内容重复，以及因缺乏或有限依据于原文而产生的幻觉问题。为通过依据原文同时提升效率与事实准确性，我们提出GroundedKG-RAG——一种将知识图谱显式地从源文档中提取并锚定于原文的RAG系统。具体而言，我们将GroundedKG中的节点定义为实体与动作，边定义为时序或语义关系，且每个节点与边均锚定于原文句子。我们通过语义角色标注（SRL）和抽象语义表示（AMR）解析构建GroundedKG，并对其进行嵌入以用于检索。查询时，我们对问题应用相同转换，并从锚定原文中检索最相关句子以进行问答。我们在NarrativeQA数据集示例上评估GroundedKG-RAG，发现其以更小成本达到与先进专有长上下文模型相当的性能，并优于竞争性基线。此外，我们的GroundedKG具有人类可解释且可读的特性，便于结果审计与错误分析。
URL
https://arxiv.org/abs/2604.04359
