Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Retrieval-Augmented Generation with Retrieval-optimized TRA Structure

AbstractRetrieval-Augmented Generation (RAG) has established itself as an innovative technology enabling Large Language Models (LLMs) to answer difficult questions beyond their internal knowledge. Graph-based RAG, which utilizes a triplet-based graph as a database, offers the advantage of structuring relationships between entities through graph connectivity, thereby capturing connections within the corpus that traditional RAG cannot express. However, this paper points out that the process of converting a corpus into a triplet-based graph using LLMs may be unsuitable for RAG due to the inability to represent hierarchical information and structural rigidity. To address this, we propose a novel database structure called the TRA(Title-Relations-Attributes) structure. Through a series of experiments, we highlight the benefits of indexing TRA Structure as a fact to utilize it as a retrieval-optimized data structure, and demonstrate its powerful multi-hop reasoning performance when combined with query decomposition, while also covering key insights in multi-hop reasoning.

More from EMNLP 2026

All EMNLP 2026 papers →