Search papers, labs, and topics across Lattice.
This paper introduces PonsRAG, a retrieval-augmented generation framework designed to overcome cognitive islanding and cross-layer evidence disconnection in long narrative reasoning. By implementing Triple-Layer Indexing and Coordinated Reasoning, PonsRAG organizes documents into a cohesive knowledge structure and retrieves evidence across distinct layers, facilitating a more integrated reasoning process. Experimental evaluations demonstrate that PonsRAG achieves an 11.56% relative improvement in accuracy on multi-choice tasks compared to the strongest baseline, highlighting its effectiveness in processing complex narratives.
Bridging cognitive islands with a novel framework, PonsRAG boosts long narrative reasoning accuracy by over 11% through innovative evidence integration.
Long Narrative Reasoning is an essential capability for processing and reasoning over complex narratives. While retrieval-augmented generation provides a promising framework, existing methods still face two critical challenges: cognitive islanding and cross-layer evidence disconnection. To address these issues, we propose PonsRAG, a coordinated RAG framework inspired by the biological pons. PonsRAG consists of two key components: Triple-Layer Indexing, which organizes documents into a connected knowledge structure to bridge cognitive islands, and Coordinated Reasoning, which retrieves evidence across distinct layers and integrates cross-layer information into a unified context. We evaluate PonsRAG on four long-context narrative benchmarks, and experimental results show that it outperforms the strongest baseline, achieving a 11.56% relative improvement in average accuracy on multi-choice tasks.
