Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916281608830976 |
|---|---|
| author | A, Aadharsh Aadhithya S, Sachin Kumar P, Soman K. |
| author_facet | A, Aadharsh Aadhithya S, Sachin Kumar P, Soman K. |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06124 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation A, Aadharsh Aadhithya S, Sachin Kumar P, Soman K. Computation and Language Artificial Intelligence I.2.7 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 |
| title | Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation |
| topic | Computation and Language Artificial Intelligence I.2.7 |
| url | https://arxiv.org/abs/2406.06124 |