RAM: Towards an Ever-Improving Memory System by Learning from Communications
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910513901862912 |
|---|---|
| author | Li, Jiaqi Wang, Xiaobo Ding, Wentao Wang, Zihao Kang, Yipeng Jia, Zixia Zheng, Zilong |
| author_facet | Li, Jiaqi Wang, Xiaobo Ding, Wentao Wang, Zihao Kang, Yipeng Jia, Zixia Zheng, Zilong |
| contents | We introduce an innovative RAG-based framework with an ever-improving memory. Inspired by humans'pedagogical process, RAM utilizes recursively reasoning-based retrieval and experience reflections to continually update the memory and learn from users' communicative feedback, namely communicative learning. Extensive experiments with both simulated and real users demonstrate significant improvements over traditional RAG and self-knowledge methods, particularly excelling in handling false premise and multi-hop questions. Furthermore, RAM exhibits promising adaptability to various feedback and retrieval methods, showcasing its potential for advancing AI capabilities in dynamic knowledge acquisition and lifelong learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12045 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RAM: Towards an Ever-Improving Memory System by Learning from Communications Li, Jiaqi Wang, Xiaobo Ding, Wentao Wang, Zihao Kang, Yipeng Jia, Zixia Zheng, Zilong Artificial Intelligence Computation and Language We introduce an innovative RAG-based framework with an ever-improving memory. Inspired by humans'pedagogical process, RAM utilizes recursively reasoning-based retrieval and experience reflections to continually update the memory and learn from users' communicative feedback, namely communicative learning. Extensive experiments with both simulated and real users demonstrate significant improvements over traditional RAG and self-knowledge methods, particularly excelling in handling false premise and multi-hop questions. Furthermore, RAM exhibits promising adaptability to various feedback and retrieval methods, showcasing its potential for advancing AI capabilities in dynamic knowledge acquisition and lifelong learning. |
| title | RAM: Towards an Ever-Improving Memory System by Learning from Communications |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2404.12045 |