MoshiRAG enables full-duplex speech language models to perform selective asynchronous knowledge retrieval during response generation to improve factuality without disrupting natural conversation flow.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models
MoshiRAG enables full-duplex speech language models to perform selective asynchronous knowledge retrieval during response generation to improve factuality without disrupting natural conversation flow.