Understand Then Memory: A Cognitive Gist-Driven RAG Framework with Global Semantic Diffusion

2026-02-11

AI Summary

This work proposes CogitoRAG, a novel retrieval-augmented generation framework inspired by human episodic memory mechanisms to address the semantic fragmentation and retrieval bias inherent in existing RAG systems that rely on discrete text representations. During offline indexing, CogitoRAG constructs a multidimensional knowledge graph by extracting semantic essences that integrate entities, relations, and memory nodes. At inference time, it employs query decomposition coupled with a graph-structured associative diffusion mechanism, enhanced by a cognitive-inspired reranking algorithm termed CogniRank, to enable human-like precise retrieval. Evaluated across five mainstream question-answering benchmarks and the GraphBench multitask suite, CogitoRAG significantly outperforms current RAG approaches, demonstrating superior capability in complex knowledge integration and reasoning.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Retrieval-Augmented Generation (RAG) effectively mitigates hallucinations in LLMs by incorporating external knowledge. However, the inherent discrete representation of text in existing frameworks often results in a loss of semantic integrity, leading to retrieval deviations. Inspired by the human episodic memory mechanism, we propose CogitoRAG, a RAG framework that simulates human cognitive memory processes. The core of this framework lies in the extraction and evolution of the Semantic Gist. During the offline indexing stage, CogitoRAG first deduces unstructured corpora into gist memory corpora, which are then transformed into a multi-dimensional knowledge graph integrating entities, relational facts, and memory nodes. In the online retrieval stage, the framework handles complex queries via Query Decomposition Module that breaks them into comprehensive sub-queries, mimicking the cognitive decomposition humans employ for complex information. Subsequently, Entity Diffusion Module performs associative retrieval across the graph, guided by structural relevance and an entity-frequency reward mechanism. Furthermore, we propose the CogniRank algorithm, which precisely reranks candidate passages by fusing diffusion-derived scores with semantic similarity. The final evidence is delivered to the generator in a passage-memory pairing format, providing high-density information support. Experimental results across five mainstream QA benchmarks and multi-task generation on GraphBench demonstrate that CogitoRAG significantly outperforms state-of-the-art RAG methods, showcasing superior capabilities in complex knowledge integration and reasoning.

Problem

• Retrieval-Augmented Generation
• semantic integrity
• retrieval deviation
• hallucination
• knowledge integration

Innovation

• Semantic Gist
• Knowledge Graph
• Entity Diffusion
• CogniRank
• Query Decomposition