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

ACL ARR 2025 May Submission6183 Authors

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 formalise 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$^2$RAG), 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$^2$RAG therefore offers a practical path to more context-aware retrieval for tasks that require precise answers grounded in chronological information.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: logical reasoning,knowledge base QA,question generation

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: English

Keywords: logical reasoning, knowledge base QA, question generation

Submission Number: 6183