Chronological Passage Assembling in RAG framework for Temporal Question Answering
This addresses the problem of temporal reasoning in narrative question answering for AI systems, representing an incremental advance by specializing existing RAG methods for narrative texts.
The paper tackled the challenge of long-context question answering over narrative tasks by proposing ChronoRAG, a novel RAG framework that refines document information into coherent passages and preserves temporal order, resulting in substantial improvements on datasets like NarrativeQA and GutenQA.
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.