Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation

2024/06/10 by Aadharsh Aadhithya A, A, Aadharsh Aadhithya, S. Sachin Kumar +3 · 1 citation
Computer Science · #Algorithms and Data Compression #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #I.2.7 #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.2406.06124

openalex publication_date 2024/06/10 · openalex created_date 2024/06/12 · openalex updated_date 2026/07/28

Abstract

Large language models have limited context capacity, hindering reasoning over long conversations. We propose the Hierarchical Aggregate Tree memory structure to recursively aggregate relevant dialogue context through conditional tree traversals. HAT encapsulates information from children nodes, enabling broad coverage with depth control. We formulate finding best context as optimal tree traversal. Experiments show HAT improves dialog coherence and summary quality over baseline contexts, demonstrating the techniques effectiveness for multi turn reasoning without exponential parameter growth. This memory augmentation enables more consistent, grounded longform conversations from LLMs

Cited by

• Teaching LLMs to See and Guide: Context-Aware Real-Time Assistance in Augmented Reality

Related

• From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
• Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
• Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning
• HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing
• Memory-Augmented Architecture for Long-Term Context Handling in Large Language Models