Chronological Passage Assembling in RAG framework for Temporal Question Answering

TL;DR

ChronoRAG is a specialized retrieval-augmented generation framework designed for narrative question answering, emphasizing temporal order preservation and structured passage assembly to improve understanding of complex stories.

Contribution

The paper introduces ChronoRAG, a novel approach that enhances narrative QA by explicitly modeling temporal order and structured passage assembly, addressing limitations of existing RAG methods.

Findings

Significant performance improvements on NarrativeQA and GutenQAdataset.

Effective in capturing temporal relationships for complex sequential reasoning.

Outperforms baseline RAG models in narrative comprehension tasks.

Abstract

Long-context question answering over narrative tasks is challenging because correct answers often hinge on reconstructing a coherent timeline of events while preserving contextual f low in a limited context window. Retrievalaugmented generation (RAG) methods aim to address this challenge by selectively retrieving only necessary document segments. However, narrative texts possess unique characteristics that limit the effectiveness of these existing approaches. Specifically, understanding narrative texts requires more than isolated segments, as the broader context and sequential relationships between segments are crucial for comprehension. To address these limitations, we propose ChronoRAG, a novel RAG framework specialized for narrative texts. This approach focuses on two essential aspects: refining dispersed document information into coherent and structured passages and preserving narrative flow by explicitly capturing and maintaining the temporal order among retrieved passages. We empirically demonstrate the effectiveness of ChronoRAG through experiments on the NarrativeQA and GutenQAdataset, showing substantial improvements in tasks requiring both factual identification and comprehension of complex sequential relationships, underscoring that reasoning over temporal order is crucial in resolving narrative QA.