RAIR combines a fine-tuned retriever, multi-turn length reflection, and adaptive selection to improve LLM-based Chinese spelling correction in equal-length and variable-length scenarios.
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
-
RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction
RAIR combines a fine-tuned retriever, multi-turn length reflection, and adaptive selection to improve LLM-based Chinese spelling correction in equal-length and variable-length scenarios.