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

TL;DR

This paper introduces a novel entity-event knowledge graph framework for retrieval-augmented generation that effectively captures temporal and causal information, improving reasoning accuracy in narrative document question answering.

Contribution

The paper presents E^2RAG, a dual-graph approach that preserves temporal and causal context, and introduces ChronoQA, a benchmark for evaluating temporal and causal understanding in narrative QA.

Findings

E^2RAG outperforms state-of-the-art baselines on ChronoQA.

Significant improvements in causal and character consistency queries.

Demonstrates the importance of temporal-causal modeling in narrative QA.

Abstract

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.