A retrieval-augmented encoder-decoder that injects 'in-context vectors' into latent states is presented, with claims of competing with much larger RAG models on three QA benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Efficient Knowledge Feeding to Language Models: A Novel Integrated Encoder-Decoder Architecture
A retrieval-augmented encoder-decoder that injects 'in-context vectors' into latent states is presented, with claims of competing with much larger RAG models on three QA benchmarks.