Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ze Yu, Li, Zitao, Li, Yaliang, Ding, Bolin, Low, Bryan Kian Hsiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918047463243776
author Zhang, Ze Yu
Li, Zitao
Li, Yaliang
Ding, Bolin
Low, Bryan Kian Hsiang
author_facet Zhang, Ze Yu
Li, Zitao
Li, Yaliang
Ding, Bolin
Low, Bryan Kian Hsiang
contents Retrieval-augmented generation (RAG) based on large language models often falters on narrative documents with inherent temporal structures. Standard unstructured RAG methods rely solely on embedding-similarity matching and lack any general mechanism to encode or exploit chronological information, while knowledge graph RAG (KG-RAG) frameworks collapse every mention of an entity into a single node, erasing the evolving context that drives many queries. To formalize this challenge and draw the community's attention, we construct ChronoQA, a robust and discriminative QA benchmark that measures temporal, causal, and character consistency understanding in narrative documents (e.g., novels) under the RAG setting. We then introduce Entity-Event RAG (E^2RAG), a dual-graph framework that keeps separate entity and event subgraphs linked by a bipartite mapping, thereby preserving the temporal and causal facets needed for fine-grained reasoning. Across ChronoQA, our approach outperforms state-of-the-art unstructured and KG-based RAG baselines, with notable gains on causal and character consistency queries. E^2RAG therefore offers a practical path to more context-aware retrieval for tasks that require precise answers grounded in chronological information.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05939
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation
Zhang, Ze Yu
Li, Zitao
Li, Yaliang
Ding, Bolin
Low, Bryan Kian Hsiang
Information Retrieval
Retrieval-augmented generation (RAG) based on large language models often falters on narrative documents with inherent temporal structures. Standard unstructured RAG methods rely solely on embedding-similarity matching and lack any general mechanism to encode or exploit chronological information, while knowledge graph RAG (KG-RAG) frameworks collapse every mention of an entity into a single node, erasing the evolving context that drives many queries. To formalize this challenge and draw the community's attention, we construct ChronoQA, a robust and discriminative QA benchmark that measures temporal, causal, and character consistency understanding in narrative documents (e.g., novels) under the RAG setting. We then introduce Entity-Event RAG (E^2RAG), a dual-graph framework that keeps separate entity and event subgraphs linked by a bipartite mapping, thereby preserving the temporal and causal facets needed for fine-grained reasoning. Across ChronoQA, our approach outperforms state-of-the-art unstructured and KG-based RAG baselines, with notable gains on causal and character consistency queries. E^2RAG therefore offers a practical path to more context-aware retrieval for tasks that require precise answers grounded in chronological information.
title Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation
topic Information Retrieval
url https://arxiv.org/abs/2506.05939