A stateful iterative RAG system converts retrieved documents into scored reasoning units, maintains supportive and non-supportive evidence, and performs deficiency-driven query refinement to achieve more robust QA performance.
Improving Negative Rejection Ability in Language Models: A Review of Fine-Tuned LLMs, RAG, and RAFT,
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
-
Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
A stateful iterative RAG system converts retrieved documents into scored reasoning units, maintains supportive and non-supportive evidence, and performs deficiency-driven query refinement to achieve more robust QA performance.