TARG uses uncertainty scores from a short no-context draft to gate retrieval in RAG, matching Always-RAG accuracy while cutting retrievals by 70-90% on QA benchmarks.
Rfid: Towards rational fusion-in-decoder for open- domain question answering.arXiv preprint arXiv:2305.17041,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG
TARG uses uncertainty scores from a short no-context draft to gate retrieval in RAG, matching Always-RAG accuracy while cutting retrievals by 70-90% on QA benchmarks.