April 22, 2024, 4:47 a.m. | Jiaqi Li, Xiaobo Wang, Zihao Wang, Zilong Zheng

cs.CL updates on arXiv.org arxiv.org

arXiv:2404.12045v1 Announce Type: cross
Abstract: We introduce RAM, 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 method …

abstract arxiv communications cs.ai cs.cl ever experience feedback framework humans improving learn memory process rag reasoning reflections retrieval type update

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne