A new benchmark on 40,000 Chinese government documents shows that token-budgeted one-shot retrieval and agentic iterative retrieval both improve RAG answer quality by about 10 points over top-k retrieval.
InNeurIPS 2023 Foundation Models for Decision Making Workshop
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
A new benchmark on 40,000 Chinese government documents shows that token-budgeted one-shot retrieval and agentic iterative retrieval both improve RAG answer quality by about 10 points over top-k retrieval.